4ffb28d41c1 : Revert property "default_applicable_licenses"
8971ef9244d : [LSC] Add LOCAL_LICENSE_KINDS to external/mesa3d
5c0bad32bae : UPSTREAM: egl: android: use num_planes param in createImageFromDmaBufs()
1a8a0f034d9 : android: softpipe: Set nir headers include path
fd5db892a5a : nvc0: Fix implicit conversion build -Werror on AOSP
1bf5d0a6f8b : mesa: i830: Fix -Wxor-used-as-pow build -Werror on AOSP
bbedfb41834 : nir: Fix implicit conversion build -Werror on AOSP
e699a9e2194 : ANDROID: Generate prebuilt-intermediate source files for mesa-20.3.4
08b1ac1c5af : ANDROID: prebuild: panfrost/Android.bifrost.mk: Use precompiled intermediate sources
b5e75a569b5 : ANDROID: prebuild: compiler/Android.nir.gen.mk: Use precompiled intermediate sources
da3fb8c4f82 : ANDROID: aosp-gen-prebuilt: Remove obsolete prebuilt targets
56030461bbb : ANDROID: freedreno/Android.ir3.mk: Fixup usage of lex/yacc
fdeee97d553 : ANDROID: Update Android.gen.bp to mesa-20.3.4
1e6cea7dc56 : [LSC] Add LOCAL_LICENSE_KINDS to external/mesa3d
517b0b214e2 : DO NOT MERGE egl: Enable eglGetPlatformDisplay on Android Platform
6d8c68603f9 : VERSION: bump version to 20.3.4
d6562bda3f0 : docs: add release notes for 20.3.4
62dc4fedeb2 : compiler: Use util/bitset.h for system_values_read
74b1a83cab0 : nir: Add a data pointer to the callback in nir_remove_dead_variables
c8245aebb5b : radv: fix divide by zero with no tesselation params
918c550950d : spirv: Don't remove variables used by resource indexing intrinsics
daa0d8668b6 : anv: Skip CCS ambiguate which preceed fast-clears
c2a6bbc712b : intel/gen12: Fix memory corruption issues in fused Gen12 parts.
e8b4805248c : panfrost: Use normal malloc/free instead of ralloc for surfaces
79eb7c245d1 : anv: Invalidate the correct AUX-TT entry
a8031d0f783 : anv: fix invalid programming of BLEND_STATE
b6310c5225e : etnaviv: handle NULL views in set_sampler_views
753f5bba85f : gallium: Fix leak of shader images on context destruction.
70e586cd0e4 : panfrost: Stub out set_shader_images().
f7918844eea : swr: Don't report support for shader images.
6e1c91eb68e : aco/optimizer: don't copy-prop logical phis
4257b873670 : aco/optimizer: don't propagate subdword temps of different size
773a46157ed : .pick_status.json: Update to f01ea0aef8a50d2732eb0c64153903e52ed2a757
431541e7913 : mesa/main: remove leftover bumpmap code
b28e674f3f3 : glx: Provide glvnd wrapper for glXSwapIntervalEXT
f155875446f : intel/fs: QUAD_SWIZZLE requires packed data
92f23b657cd : intel/compiler: Return 1 for immediates in regs_read
5fc1fe85482 : .pick_status.json: Update to 9052819ebbff07d82c3eb9adf414144df4868644
c5577bed0e8 : frontends/va/context: don't set max_references with num_render_targets
06fadeeda7b : zink: make all xfb caps depend on extension
199fb00815f : zink: respect feature-cap for sample-shading
3efcf3b34f7 : zink: respect feature-cap for independent blending
613251e8519 : aco: don't consider a phi trivial if same's register doesn't match the def
127e9ef4563 : iris: Consider resolves after changing a resource's aux state
c2932690c63 : radv: fix a sync issue with geometry shader primitives query on GFX10+
d038bd7b3ed : pan/decode: Free mapped memory objects on BO unreference
5fc12bcbc00 : anv: Fix stencil layout in render passes
7d168e8f24f : .pick_status.json: Update to 3ef89b245e3e1ac4e67fea9c1b13ebeda75769d0
a098a704a41 : st/mesa: fix pbo upload/download for arrays of textures with only 1 layer
2ed63e74616 : ci: exclude one CTS test that timeout most of the time for RADV CI
44d9a7f6fba : .pick_status.json: Update to af9977a3d5f3378c297965e21389e36491f47e1b
b944f5a65c2 : Fix license_type. Contains AMD and GPL
4fab4ed028d : swr: fix crashes caused by incorrectly reporting SSBO support
79b792e4618 : aco: fix convert_to_SDWA() check in add_subdword_definition()
0d1920b6c57 : mesa: fix alpha channel of ETC2_SRGB8 decompression for !bgra
381a5de3eaa : zink: handle NULL views in zink_set_sampler_views
6e2e95a318d : glsl: only expose int64 atomics when extension is enabled
0aa060c5b41 : lavapipe: fix missing piece of VK_KHR_get_physical_device_properties2
8eb3a0b6cb7 : Fall back on clock_gettime when timespec_get() is unavailable
affb8eebe40 : device-select-layer: update for vulkan 1.2
e8755481ce1 : util: Fix pointer to integer conversion error when using libunwind
a6e9b3644aa : util/format: Fix pack/unpack of A1R5G5B5_UINT.
4fb89e0f381 : .pick_status.json: Update to 3e13c1f8dfef4a4c0fd5e79bbc364f9e5f998856
1d0a7bb5203 : intel/mi_builder: fix self modifying batches
d4a0136e268 : v3d: fix dest offset in TFU setup
d5ee8416e27 : iris: only set point sprite overrides if actually using points
851d753c1b6 : .pick_status.json: Update to c27347b2e1883a30e023347a36bdcf86cdec4a7c
205e8cd0935 : radeonsi: invalidate compute sgprs in si_rebind_buffer
bfb6f66934f : anv: add transfer usage for color/depth/stencil attachments
cb24282b01f : lavapipe: Defer lavapipe warning to CreateDevice
3398f1c862a : frontends/va: Return an error if non-interlaced buffer is not supported
8d20fc6a855 : .pick_status.json: Update to 184bbef33d1fff3520958c130f2b8e4fce17379c
326d21431c4 : docs: Add sha256sum for 20.3.3
7e4d536e630 : VERSION: bump to 20.3.3
884c86d74e0 : docs: add release notes for 20.3.3
24c7a4df3a8 : vulkan/overlay: fix vkGetInstanceProcAddr self-resolving
b439d0e679c : radv: Add Android module info to linker script.
3261d99b9c0 : mesa/st: Free the NIR builtins TGSI tokens after passing to the driver.
ed87818eddb : gallium/ntt: Fix leak of the per-instr liveness information.
adf09c9bf0e : radv: set invariantgeom for Shadow of the Tomb Raider
f8033bdc6d6 : radv: add RADV_DEBUG=invariantgeom
97365ce754e : vulkan/overay: fix violation of VUID-VkDeviceCreateInfo-pNext-00373
945bffe0087 : vulkan/device-select: fix vkGetInstanceProcAddr self-resolving
c5f73e66ed6 : radv/winsys: Fix offset in range merging.
107e4eea53e : radv/winsys: Fix inequality for sparse buffer remapping.
bf4e0a4b3e1 : .pick_status.json: Mark 52b6adfbfb51a3b1a54964cbcb2adb0299d1252b as backported
bbb85a7be00 : util: Avoid pthread_setaffinity_np on NetBSD
76ecdf2c322 : aco: fix unreachable() for uniform 8/16-bit nir_op_mov from VGPR
6a006c35675 : util: Disable memstream for Apple builds
e6aa51a84d5 : radv/llvm,aco: always split typed vertex buffer loads on GFX6 and GFX10+
a29f08b1e20 : aco: fix creating the dest vector when 16-bit vertex fetches are splitted
eec614e0f31 : nir/load_store_vectorize: don't ignore subgroup memory barriers
2c5b5920ca6 : .pick_status.json: Update to d9c8422c4168c7433f68b97065283ebf26631d56
aef8fc860c2 : drirc: radeonsi workaround for CS:GO
ae1c5dc6b68 : radv: disable TC-compat HTILE in GENERAL for Detroit: Become Human
9000c044fbd : zink: dot leak dummy_buffer
39c386c0fdc : nir/algebraic: Fix broken NaN and -0.0 behavior
72233905e36 : Revert "nir: Replace an odd comparison involving fmin of -b2f"
588cf800be8 : gallium/util: do not perform n^2 stencil blits
cf5fe357d6b : gallium/ntt: Fix emitting UBO declarations.
071a87ac7f9 : ac/nir: use llvm.readcyclecounter for LLVM9+
e9146fe6fb4 : util: add AMD CPU family enums and enable L3 cache pinning on Zen3
20a067a837a : spir-v: Mark floating point comparisons exact
f121623020b : st/mesa: don't affect original st_CompressedTexSubImage parameters
773d683a898 : .pick_status.json: Update to 96ceca33c1dd69a1feed13b0e19bfc38e6f7d979
da6fb037775 : aco: fix incorrect address calculation for load_barycentric_at_sample
2f9e5cae2bc : nir: fix missing nir_lower_pntc_ytransform.c in the makefile
9e1e67b35b8 : nir: account for point-coord origin when lowering it
d7c09d09aa0 : etnaviv: Fix rework ZSA into a derived state
b83d96666dd : .pick_status.json: Update to b2d000513e4a9b06d3b073913741dae47a00526e
99ff47e8538 : st/mesa: don't do glCopyPixels via blit if depth bounds test is enabled
636a917ca4c : pan/mdg: Fix promoted uniform moves with 64-bit types
c7430bbc3eb : nir: fix determining if an addition might overflow for phi sources
2b66910037b : gallium/draw: Fix intermittent failure to bind new geometry shaders.
2f6f5b3ba24 : .pick_status.json: Update to 9ef2c44ce682b7981bd7a68c65f338f1e33bb001
6d2e76d2425 : docs: Add sha256 sum for 20.3.2
b3877e880ba : Bump version for 20.3.2 release
d9d99af1560 : docs: add release notes for 20.3.2
7ca951d11ad : glsl: default to compat shaders in compat profile
e8a6bf6e103 : st/pbo: fix pbo uploads without PIPE_CAP_TGSI_VS_LAYER_VIEWPORT and skip gs
f892a46cc54 : virgl: fix BGRA emulation artifacts during window resize
b62bd28ec86 : .pick_status.json: Update to 6c8cc9be12dc5d6c0d2386d6addb69d8f2fb5399
b21d6928056 : .pick_status.json: Mark 967ae12931e0dc12855de903851222b2f0607878 as denominated
009e2aa5460 : zink: handle null ubos
b0e8fb53ba9 : ci/deqp: Fix inverted meaning of DEQP_NO_SAVE_RESULTS.
373b6eba5f2 : mesa/st: Update FP state when textures change with an ATI_fs bound.
7c74888039a : radeon/vcn: fix hevc 10bit profile error
2fd551d4f3c : softpipe: count CS invocations for pipeline stats queries.
cc7a1ab3456 : .pick_status.json: Update to 9ef23e428bd18c412499471b4e3550a489b72c3f
b41a3c8a1d4 : turnip: use ir3_compiler_destroy instead of ralloc_free
b4cbf3776a7 : panfrost: Fix panfrost_small_padded_vertex_count for 17 vertices
6e75f406f80 : .pick_status.json: Update to a22b85ce5e825275533ca1be9fbd47667e991356
fb689963da6 : radv: Don't skip layout transitions that only differ in render loop.
e2789cd78eb : ir3: Allow tesselation to use all 32 varying slots
633f60ee573 : freedreno/a6xx: Fix assert which checks the count of shader outputs
eec213d2adc : mesa: fix layered framebuffer attachment target check
27e6dfb06a1 : .pick_status.json: Update to 8db0775f4520e08b3c539f9bd2d1f567639c088c
5e632582d01 : Fix build issue when USE_3DNOW_ASM is not defined
50b977737e6 : freedreno/a6xx: Flush depth at the end of bypass rendering, too.
d54de72aa0e : spirv: Remove more dead variables
a46b833725f : nir: Consider pointer initializers in nir_remove_dead_variables
d5a9377096a : .pick_status.json: Mark f65750d2215242b17309b5aa8845b717bb913e77 as backported
d9063a077ff : .pick_status.json: Update to b9fccafed616aa2906dad3c77dca0c67af5017b8
a5f47bc43d6 : spirv: Implement OpArrayLength for OpenGL
f99fc9e73e3 : zink: fix format-mapping
c00c8d8c91d : mesa/st: Finalize the texture before BlitFramebuffer from it.
8232610da2d : nir/opt_if: split ALU from Phi more aggressively
79c2aeabebf : .pick_status.json: Update to f65750d2215242b17309b5aa8845b717bb913e77
4ba1dba7acb : aco: add block to worklist in mark_block_wqm()
19b92b771a9 : tu: pCounterBuffers can be NULL in vkCmd*TransformFeedbackEXT()
81421b7dd4e : tu: Ignore pTessellationState if there is no tesselation shaders
abfbaa8476f : radv: add missing DB flush after depth/stencil resolve operations
8217078f007 : aco/ra: fix phi operand renaming
59a94717ff0 : egl: fix EGL_EXT_protected_content/surface mixup
cf1af4a6631 : .pick_status.json: Update to 661922f6ac9576fc2077c5d50b53ef7edf9e8a18
840a9a6c67b : radeonsi: fix small primitive culling with MSAA force-disabled and smoothing
4a87e444134 : aco/spill: only prevent rematerializable vars from being DCE'd if they haven't been renamed
c9497e286d3 : aco: fix DCE of rematerializable phi operands
5636ec0acec : st/mesa: set drawpixels swizzle before creating sampler view
cf0f7d243e0 : zink: fix 8 bit index handling code
e53124546b2 : .pick_status.json: Update to 2d78e28ba702d366becabb8e241b861e6711c76e
3ae62ab7720 : docs: Add sha256 sums for 20.3.1
d90622910ba : VERSION: bump for 20.3.1
d4f4d29a6cf : docs: add release notes for 20.3.1
adb6c1cc0ab : gallium/dri2: Don't forget protected content flag
6c2b0d7a810 : anv: Add DRM_RDWR flag in anv_gem_handle_to_fd
7c0e171c970 : .pick_status.json: Update to ada9be1ec9e14fc045086411fbf2d3cb0efbbe2f
7d5c0483867 : radv: fix access to uninitialized radeon_bo_metadata
c04030308db : st/pbo: fix pbo uploads without PIPE_CAP_TGSI_VS_LAYER_VIEWPORT
62eea2b34ca : zink: really fix direct image mapping offset (I mean it this time)
f9bc767bdc5 : nir: Redefine start/end_ip of blocks to fix NIR-to-TGSI liveness bugs.
f5246efd8df : zink: fix direct image mapping offset
07d6fa2aba9 : .pick_status.json: Update to a7fb3954a1318a6b27e1405a9e799dd8f06eaa34
200a2f24551 : aco/ra: use get_reg_specified() for p_extract_vector
5e65a36a7f8 : aco: Use program->num_waves as maximum in scheduler.
ac1145f704a : android: fix build failure with libbacktrace
18d5fe46e53 : .pick_status.json: Update to 84c8a35aa2ca4d4de66192933735094ed07b4aaa
4631f3848c3 : radv: do VGT_FLUSH when switching NGG -> legacy on Sienna Cichlid
7bf1fbea733 : radv: fix applying the NGG minimum vertex count requirement
317526ec2f4 : radv: don't count unusable vertices to the NGG LDS size
7b1ee981570 : radv: disable SQTT support for unsupported GPUs
2ae373152ae : radv: ignore other blend targets if dual-source blending is enabled
67a3b8ec236 : aco: fix combining max(-min(a, b), c) if a or b uses the neg modifier
bd7ccbf214d : zink: fail if set failed to create
bd01bc1f681 : radeonsi: fix si_get_draw_start_count count value
4691bc5d201 : ci: .lava-test:amd64 template needs arm_build
c763926c763 : anv: fix calculation of buffer size in case dynamic size is used
e0d212c856d : .pick_status.json: Update to cf3fc79cd0ab55776bbbabe76237c272ab07133e
18fd2554021 : turnip: no linear_to_srgb for alpha channel for gmem clear value packing
5d24ae64c9f : iris: Fix resource ptr in resolve_sampler_views
7f485f1e8f8 : softpipe: Fix swizzled texture gather of int textures.
4e05bd1d134 : panfrost: Fix fencing
93ac6a935fe : panfrost: Make sure we always add a reader -> write dependency when needed
c8655229124 : iris: update depth value for stages after fast clear depth
c20c50e6efc : android: spirv: fix '::' typo in gen rules
b9dbeb597f3 : turnip: always set LRZ registers to zero for 3d clear/blit
e9407a0a4f8 : turnip: move up LRZ invalidate in CmdClearAttachments
4c32042db77 : turnip: always emit LRZ draw state in DIRTY_DRAW_STATE path
51e8c7ec9a2 : .pick_status.json: Update to 3f0da800eb4b8184c24707c52d5a519abe948898
a8d5e57590b : iris: fix memleak for query_buffer_uploader
1c83ec979f5 : aco: use UINT64_C on 64 bit constant arguments
0c2b29e3ac3 : radv: disable alphaToOne feature
ee83c989f6b : zink: Cap PIPE_SHADER_CAP_MAX_CONST_BUFFERS to 32
c5ffe9e0f2a : zink: fix channel ordering in format-mapping
17ef9b55d09 : gallium: do not reset buffers for unsupported stages
d77d3caeca6 : .pick_status.json: Update to f93b7d14d66d8ba70d44772d1a1b6696310b7d17
0cde14200a4 : ci: Drop x86_build_old image
b3bfb017189 : radv: fix exporting multiviews with NGG
33c288361c2 : radv: mark GFX10.3 as a non-conformant Vulkan implementation
44bed805065 : radeonsi: fix regression on gpus using the radeon winsys.
dfadf838aef : meson: Fix Clang microsoft-enum-value detection.
03e8cc7ca9b : .pick_status.json: Update to ec3828add38a83b8c09fd5896265abc9d766162e
13e7057e790 : aco: don't assume src=lower when splitting self-intersecting copies
bd95f95dc56 : iris: store copy of the border color in the border color hash table
03802858b47 : .pick_status.json: Update to 72b68bd2a62d193e26bd6b31123182d7dbae3098
ec22eb7efbc : .pick_status.json: Mark a5e0a2e101bcda0132185a82c3e8c9b4c90ce94c as denominated
9465b0eb8ca : .pick_status.json: Update to 872c4bcd27db7b7ca26abe9fc090ae26d502156f
a8650e97230 : docs: Add sha256 sums for 20.3.0
08169ff176b : bump version for 20.3.0 final
b9d2f63f2f8 : docs: add release notes for 20.3.0
404c4400156 : freedreno: Break out of "should we free the entry" loop once we've freed.
01f9a5e8227 : gallium: Fix leak of currently bound UBOs at CSO context destruction.
faeaa8171e3 : gallivm: Fix max const buffer count.
8258c5867af : gallium: Fix leak of bound SSBOs at CSO context destruction.
d0d3a589a18 : freedreno: Fix leak of u_transfer_helper.
0ee24d08fa2 : gallium: Fix leak of the merged driconf options.
531b15c22ad : zink: do not require VK_KHR_external_memory
cddf1bf5f9b : freedreno: Add missing dependency to build
12c40b04770 : radv: Fix leak in radv_amdgpu_winsys_destroy()
1578dde278d : radeonsi: disable WGP mode on gfx10.3 to prevent hangs
2b9da404c1a : radeonsi: fix a nasty bug in si_pm4.c
b7659c5ed76 : radeonsi: fix a memory leak in si_create_dcc_retile_cs
4e39cdaa508 : .pick_status.json: Update to d3c67d7e7ec6b9cf10fbea0d08e92751b7b0fbae
bcbc20bf6ec : nir/algebraic: Avoid creating new fp64 ops when using softfp64
7a4f33b1f5b : aco: Fix NGG GS assert failure from the WG scan.
f4a059eb988 : etnaviv/drm: fix evil-twin etna_drm_table_lock
b52bb0dc5c0 : st/mesa: fix uninitialized/random clip plane state vars in lower_ucp
770f46c7811 : mesa: call FLUSH_VERTICES before changing sampler uniforms
ded8b21e2a4 : radv: Deal with unused attachments in mip flush
db68b97f255 : r600/sfn: fix component loading from fixed buffer ID
5355ff37441 : radv: Fix a hang on CB change by adding flushes.
25f01a7d4b7 : docs: document new zink-flag
3e2a3b402bb : nir: fix sampler_lod_parameters_pan indices
1891d300310 : freedreno/a6xx: Fix typo in height alignment calculation in a6xx layout
bf76f2b21c1 : anv: fix descriptor pool leak in VMA object
099804865ad : aco/optimizer: Only set scc_needed when it is actually needed.
6e72700f842 : glsl: avoid an out-of-bound access while setting up a location for variable
0eabed30a43 : radeonsi/gfx10: flush gfx cs on ngg -> legacy transition
bfb711b2099 : nir/unsigned_upper_bound: fix buffer overflow in search_phi_bcsel
9c6e0fb4761 : aco: fix v_mul_hi_u32_u24 format
7770f9a27df : .pick_status.json: Update to 89f6b72f19dbc503386643c6283047bdb1013bef
39bfa34231d : bump VERSION for 20.3-rc3
45f5e8d4559 : appveyor: disable for now
e1e31f6126c : radv: Fix RB+ blending for VK_FORMAT_E5B9G9R9_UFLOAT_PACK32.
b2c70c3b116 : spirv: Call repair SSA for OpTerminateInvocation
deccfbc0d77 : zink: fall back to util_blitter for scaled resolves
0464d64d6ce : gallium: fix missing bit field in p_state.h
e9cdf398fa2 : lavapipe: enable pipeline stats queries
10a9d8a10f4 : lavapipe: fixup mipmap precsion bits
092a65b0d13 : llvmpipe: fix multisample lines.
7e90c4d148e : llvmpipe: fix multisample point rendering.
ad4d87a5373 : llvmpipe/setup: move point stats collection earlier.
904811faacc : lavapipe: fix wsi acquire fences
6e3894d52d1 : lavapipe: fixup device allocate + enable private data
c7fdc10cbad : zink: fix layered resolves
0a393505726 : meson: Don't add extra values to shader-cache
f998d5bddbd : .pick_status.json: Update to 9fa1cdfe7ffd9e7ebd83055e2008f3e4b8ada549
162a0678ac3 : aco: fix combining add/sub to b2i if a new dest needs to be allocated
8464a6e3d7b : v3dv/cmd_buffer: missing (uint8_t *) casting when calling memcmp
60bf76735c8 : ac/nir: fix a typo in ac_are_tessfactors_def_in_all_invocs
6adf918d341 : r600/sfn: lower bool to int32 only after common optimizations
29f1078c18c : nir: fix gathering patch IO usage with lowered IO
33d70876820 : nir: fix gathering TCS cross invocation access with lowered IO
48bcf3bcc39 : meson: drop deprecated EGL platform build options
921bd0eabed : gitlab-ci: drop deprecated platforms that snuck in when nobody was watching
f56cbdf9951 : .pick_status.json: Update to a92f597b98bb032b904c7c8a8c3a9fe798b51915
43697f6c5fc : intel/compiler: Rotate instructions ROR and ROL cannot have source modifiers
2d1e15236b0 : .pick_status.json: Update to a59b1b18a95af1f8edb0093baf508e974e3251a2
d8e73329ded : ac: Don't negate strstr return values in ac_query_gpu_info
84e77da244e : intel/fs: Fix sampler message headers on Gen11+ when using scratch
e1697827104 : freedreno: Fix warning about uninit size for the size==0 special case.
650e2a15ad3 : radeonsi: fix scan_instruction for bindless inc_wrap/dec_wrap atomics
2ce2c22d1ad : radeonsi: fix NGG streamout regression
5bf5eb452f5 : ac: fix min/max_good_num_cu_per_sa on gfx10.3 with disabled SEs
32b5779ade5 : ac: fix detection of Pro graphics
f396e154f1d : radeonsi: add options.inline_uniforms to the shader cache key
d247a0720af : radeonsi: determine correctly if switching from normal launch to fast launch
cd3cd167838 : radeonsi: only do VGT_FLUSH for fast launch if previous draw was normal launch
fe27a78d315 : radeonsi: do VGT_FLUSH when switching NGG -> legacy on Sienna Cichlid
825a8846cc4 : radeonsi: fix min_direct_count value
40e3de32e13 : bump VERSION for 20.3.0-rc2 release
0201fc95e7f : glcpp: Handle bison-3.6 error message changes
827c0cc14f7 : .pick_status.json: Update to bac6cc586fe4c1b24351e0574d3a961eb631f6ae
654376faad6 : anv/image: Fix isl_surf_usage_flags for stencil images
c9d10b391c1 : anv/image: Check DISJOINT in vkGetPhysicalDeviceImageFormatProperties2 (v2)
1534e28669d : zink: more accurately track supported blits
f076b4d3ab9 : turnip: Close sync_fd only if it is a valid file descriptor.
f6a73228a47 : clover/spirv: Add missing break for SpvOpExecutionMode case.
5953d04aec1 : frontends/va: Fix *num_entrypoints check.
94f202c6bc5 : freedreno: Fix leak of shader binary on disk cache hits.
d7366262d2b : etnaviv: fix disabling of INT filter for real
ce29a107f43 : mesa/main: add missing include in glformats.h
9d399939e08 : aco: fix fp16 *0.5 omod
dc0580d3441 : aco: disable omod if the sign of zeros should be preserved
ded5cd528a9 : iris: initialize shared screen->vtbl only once
15367d29693 : egl/dri2: fix race between image create and egl_image_target_texture
ee3ed20f3d8 : draw: fix tess eval pipeline statistics.
e5327be5acb : etnaviv: nir: do not run opt loop after nir_lower_bool_xxx(..)
b8ddfc0bb78 : vdpau: Add missing printf format specifier.
159ded94814 : freedreno/ir3: Fix crash in shader compile fail path
4de41dea583 : panfrost: Fix stack shift calculation
b37d613da5b : mesa: Clamp some depth values in glClearBufferfi
d47cb4124ac : mesa: Clamp some depth values in glClearBufferfv
5b83eb0b098 : mesa: Add and use _mesa_has_depth_float_channel
14167715ccc : .pick_status.json: Update to 87dc3106b077199b829a082e32ec33d0c6d400ab
004b8b105ff : aco: disallow various v_add_u32 opts if modifiers are used
46ab4f91710 : aco: fix combine_constant_comparison_ordering() NaN check with 16/64-bit
afe279ad861 : aco: don't combine precise max(min()) to med3
cdb5bcc0598 : turnip: Fix file descriptor return.
0724abde7a3 : gallium/draw: Fix rasterizer_discard for wide points/lines.
0e3bb4aa913 : mesa: Fix vertex_format_to_pipe_format index.
7762b3cda4c : nir: handle float atomics in copy propagation pass
fe8c524c826 : intel/fs: Fix use of undefined value in fixup_nomask_control_flow
51d4d91f7d2 : ci: Only install kernel modules for LAVA devices.
a442fc2955e : llvmpipe: just use draw_regions in draw/line setup.
bc3e92a1df1 : lavapipe: disable SNORM blending for now
0e4e0a0d09a : lavapipe: enable alpha to one.
3ee324d4ec1 : u_blitter: port radv 3D blit coords logic.
4de4f552289 : gallium: handle empty cbuf slots in framebuffer samples helper
f4d976d5917 : util/set: Fix the _mesa_set_clear function to not leave tombstones.
966b55c6dae : freedreno: Protect gmem_cache ralloc allocations
60ffcfe6a98 : st/mesa: fix use-after-free when updating shader info in st_link_nir
46c08b73dea : softpipe: correct signature of get_compiler_options
23f4120491d : panfrost: Fix ->reads_frag_coord assignment
f3ff1265ba7 : panfrost: Fix Bifrost blend descriptor emission
5c167e8d923 : pan/bi: Model writemasks correctly
2940fb13eba : panfrost: Fix AFBC blits of resources with faked RGTC
5634699a2c0 : .pick_status.json: Update to bf5cea7232f9ee2934c212211ebefb6fe766526d
f44896c12ac : bump version for 20.3-rc1
3c4e43e72be : intel: Pointer to SCISSOR_RECT array should be 64B aligned
a1a365e8188 : broadcom/compiler: Allow spills of temporaries from TMU reads
1c5271346af : nir/algebraic: optimize bitfield_select(a, b, 0) to iand(a, b)
d47969eb5ed : pan/bi: Add support for load_instance_id
5cd1d8c1ed9 : pan/bi: Add support for load_vertex_id
255f7842c7c : panfrost: Allow linear ZS resources on Bifrost
4995a4c03aa : pan/bi: Add support for ushr
af70987b363 : pan/bi: Add support for ishr
3257ad21f34 : pan/bi: Fix ARSHIFT definitions
2a80b2d0cd1 : pan/bi: Move bitwise op packing out of bi_pack_fma()
cc0950722c0 : pan/bi: Get rid of bi_emit_ld_uniform()
fd265fa0206 : pan/bi: Lower uniforms to UBO
09da82cbdc3 : pan/bi: Add support for load_ubo
87e2169cb90 : pan/bi: Fix swizzle handling in bi_copy_src()
2522f509a3d : pan/bi: Support centroid and sample interpolations
ca5a00a70ca : pan/bi: Extract LD_VAR sample field from ins->load_vary.interp_mode
1692088d053 : panfrost: Expose GLES3 features on Bifrost when PAN_MESA_DEBUG=deqp
23dbf7964b7 : panfrost: Force late pixel kill when depth/stencil is written from the FS
956228da3a1 : radeon/vcn : Corrected dpb_size calculation for VP9_2
68092df8d88 : intel/nir: Lower 8-bit ops to 16-bit in NIR on Gen11+
b98f0d3d7c3 : intel/nir: Lower 8-bit scan/reduce ops to 16-bit
3ad2d85995e : intel/nir: Refactor lower_bit_size_callback
f95665cfebb : nir/lower_bit_size: Add support for lowering subgroup ops
2c4b47184da : nir/lower_bit_size: Pass a nir_instr to the callback
15c6e05a725 : nir/lower_bit_size: Don't cast comparison results
86ef139bf46 : radv: implement VK_EXT_shader_image_atomic_int64
9f432687726 : ac/nir: implement 64-bit images
5b81e80fb6c : aco: implement 64-bit images
8570de72f51 : amd/common: add PIPE_FORMAT_R64_{UINT,SINT} to GFX10 format table
cff195087f5 : util: add mapping from Vulkan to Gallium R64 integer formats
bcc3d53587a : gallium: Fix NIR validation when lowering polygon stipple
441feda0bb3 : gallium/util: do not pass undefined sample-count
bae54876596 : aco: optimize v_and(a, v_subbrev_co(0, 0, vcc)) -> v_cndmask(0, a, vcc)
2bbe01b186b : spirv: Add support for SPV_EXT_shader_image_atomic_int64
5a3e22018d1 : nir: Allow 64-bit image atomics
79f477c3c60 : compiler/types: Add 64-bit image types
d44c76be85f : util,gallium: Add new 64-bit integer formats
b725fbd1913 : nir: Validate image atomic formats
72f1c9aef5d : nir: Print formats on image intrinsics as text
d22fafa20b7 : spirv: Update headers and metadata from latest Khronos commit
2acdcf0b317 : libgl-gdi: support building without softpipe
d7f7d890f15 : panfrost: Add missing Collabora copyright notices
14bbc24b60c : pan/mdg: Add missing Collabora copyright notices
92374aebe2d : spirv: correct sematic-typo
fc2814417e9 : CI: Disable Panfrost T760
4143572f93e : radeon/vcn: Bitrate not updated when changing framerate
25066eb20a2 : v3dv/device: do nothing when asked physical device pci bus properties
ca1969ca880 : v3dv/util: log debug ignored stype only on debug builds
1fa4a372568 : v3dv/util: remove several logging functions
1675c83a4fc : radv: Fix exporting/importing multisample images.
fb1793bf9c8 : zink: add some spirv builder functions for barriers
95e15f774dc : zink: add a quadop function in spirv_builder
758e932ad27 : zink: use same function for all pipe_context::delete_*_state shader methods
d377d844969 : zink: make physical device functions use a dynamic function pointers.
91f9bc18e0c : radv: Fix budget calculations with large BAR.
9948ead3cd4 : radv: Skip tiny non-visible VRAM heap.
b7793e39ee4 : docs: update calendar and link releases notes for 20.2.2
e053a02ee97 : dcs: Add sha256 sums for 20.2.2
5e1f518f30b : docs: add release notes for 20.2.2
39d1576eef0 : st/nine: Remove unnecessary NULL check.
0bc222706d3 : zink: implement ARB_texture_query_lod
bf29daa1b5a : ci/deqp: Switch to a new dEQP runner written in Rust.
fe61230b38f : ci/bare-metal: Reset colors at the end of a line of serial output.
ff6741728de : ci/bare-metal: Apply autopep8 to the bare-metal scripts.
9f1cd99ba12 : turnip: Fix image size for 3D vkGetImageSubresourceLayout.
a0b42da0a2e : spirv: fix GLSLstd450Modf/GLSLstd450Frexp when the destination is vector
81597759bef : zink: For MoltenVk added vkFlushMappedMemoryRanges() to vkMapMemory() to fix empty mapped memory.
f0bbd8fdd08 : zink: have_triangle_fans support.
2aca3749c57 : zink: add support to device info for macro guards and just VkPhysicalDevice*Features with out the have_.
f0a88dbefa6 : nir/lcssa: consider loops with no back-edge invariant
feb9462bb19 : zink: Added inbuilt debug logging from the VK_LAYER_LUNARG_standard_validation layer.
10d44fec2dd : zink: fix pNext chain for resource memory allocation
0b53ca0cca9 : zink: return fail if create_instance fails
6a967294487 : docs/features.txt: VK_EXT_separate_stencil_usage not exposed on RADV
6ec7e0d4066 : gallium: document convention for get_handle calls on multi-planar resources
b29fe26d438 : etnaviv: rework ZSA into a derived state
3c7fc95f4fe : etnaviv: expose shader discard usage in etna_shader_variant
bff60d665b8 : etnaviv: update headers from rnndb
83c72cab7a1 : etnaviv: flush depth cache when changing depth config
01e2ded11f7 : etnaviv: emit RA_EARLY_DEPTH on dirty ZSA
d4285805345 : mesa/st: use a lock to protect access to variants when updating them
77d6fda0f50 : nir/algebraic: distribute imul(iadd(a, b), c) when b and c are constants
2fd5079442c : clover: implements clSetContextDestructorCallback
04e1b1757cf : clover: add empty cl 3.0 dispatch entries.
558325c4c50 : clover/spirv: hook up spir-v environment for 3.0
7230f39c1a2 : clover/llvm: add 3.0 versioning.
a52c613ea7d : clover: access 3.0 and deprecated 2.2 API
9790fdf2ceb : vtn/opencl: add ctz support
725df7c15dc : CL: update CL headers to 3.0
041e3147c05 : docs: Add MESA_pack_invert and ANGLE_pack_reverse_row_order
fd104096c61 : mesa: Implement GL_ANGLE_pack_reverse_row_order
4506e4db4d6 : mesa: Enable GL_MESA_pack_invert unconditionally
923577c0662 : v3dv: Remove unsigned comparison to zero.
03683b9b2e6 : nir: Handle ray-tracing intrinsics and storage classes in copy-prop etc.
5a288932797 : spirv,nir: Add ray-tracing intrinsics
21b1b915498 : nir,spirv: Add support for the ShaderCallKHR scope
6b8fd65e840 : spirv: Implement the new ray-tracing storage classes
84a8ca1db88 : nir: Add new variable modes for ray-tracing
aa4ea9c7ea6 : nir: Add intrinsics for object to/from world RT sysvals
07635a3284c : nir/builder: Add a select_from_ssa_def_array helper
46cd91bb45a : spirv,nir: Add support for ray-tracing built-ins
ed907e5d84c : spirv: Add support for OpTypeAccelerationStructureKHR
2df055ab47f : spirv: Pass the deref type to storage_class_to_mode for non-forward pointers
2bef02696d4 : spirv: Add a guard for OpTypeForwardPointer storage classes
aabe37b9694 : spirv: Remove a redundant vtn_fail_if
3bcebe1b271 : spirv: Add Ray Tracing execution models
d8dbdf20de8 : spirv: Add basic plumbing for ray-tracing capabilities
f65182931db : compiler: Add new Vulkan shader stages
1882a02d83b : tu: Make sure spirv_to_nir knows we support imageStorageWithoutFormat.
0b0f152c54e : nir/clip_disable: handle 2x vec4 case
5e43ba39e11 : nir/clip_disable: try for better no-op
1d23a88c6eb : nir/clip_disable: write 0s instead of undefs for disabled clip planes
c84ae1523e0 : iris: Move blit scissoring earlier.
0f96a9ab3b0 : anv: restrict number of subgroups per group
b2c719308c5 : turnip: enable VK_EXT_image_drm_format_modifier
f624692a57d : turnip: don't always fallback to linear for mutable formats
8c4426f519c : turnip: remove unnecessary/redundant tu_image fields
c64cd6988f1 : turnip: remove useless tu_image asserts
dfaa8b9ae72 : turnip: LAYOUT_PREINITIALIZED is not different for optimal tiling
43c16483e0b : turnip: don't implement CreateImage as two separate functions
1a1099c54f1 : aco: Fix format string used when raising validation errors
61d2badbf47 : nir/deref: Fix a typo
60c5729d166 : ci: Distribute ADMGPU driver to LAVA as a module
bb41acf96af : ci: Update dEQP skips and fails for Bifrost on G52
80cbb324434 : ci: Update kernel for LAVA to 5.10-rc2 plus patches
092186d9857 : util/threaded_context: use driver's buffer alignment for staging transfers
60b9c00afd2 : v3d: Add GL_ARB_vertex_array_bgra support
9648bfba564 : v3dv: mark the right bit to swap R/B vertex attributes
1e723745dde : v3d/compiler: extend swapping R/B support to all vertex attributes
44925a8a554 : intel/tools: add missing new lines to few remaining fail_if users
c323d7c2a7f : intel/tools: refactor logging to be easier to follow by static analyzers
f0061277c00 : intel/tools: handle some failures
cd9907e7d39 : anv: remove dead code from anv_create_cmd_buffer
d13b7d65914 : intel/tools: allow --color option to be used without arg
0dad1a7c72a : v3dv: expose more features
0b30336906f : broadcom/compiler: Handle non-SSA destinations for tex instructions
e331fd7fc42 : vc4: use intmax_t for formatted output of timespec members
c8630fd1143 : amd/addrlib: Add missing va_end.
fe52efaa98e : loader: Print dlerror() output in the failure message
5d5f3e3a477 : intel/fs: Implement nir_intrinsic_{load,store}_shared_block_intel
9fe158e1d10 : intel/fs: Implement nir_intrinsic_{load,store}_ssbo_block_intel
d372abe3973 : intel/fs: Add surface OWORD BLOCK opcodes
296137df53a : intel/fs: Implement nir_intrinsic_{load,store}_global_block_intel
d3d2b73fa3c : intel/fs: Add A64 OWORD BLOCK opcodes
eb03f29655c : spirv: Implement SpvCapabilitySubgroupBufferBlockIOINTEL
dd39e311b33 : nir: Add nir_intrinsic_{load,store}_deref_block_intel
b86ce274f9d : spirv: Implement SpvCapabilitySubgroupShuffleINTEL from SPV_INTEL_subgroups
5194cbc7663 : iris: Flush dmabufs during context flushes
c488fb6dfec : iris: Fix fast-clears of swizzled alpha formats
60336cac601 : iris: Fix SINT assert in convert_fast_clear_color
4cb9b5db2ce : iris: Fix fast-clears of swizzled LA formats
382451ff9d7 : iris: fix source/destination layers for 3D blits
61ce544d070 : st/nir: Drop setting interp mode on system values in builtins.
9143c08125a : st/nir: Fix the st->pbo.use_gs case.
f8c1d79f69a : pan/bi: Correctly calculate render target index
9a6dad18d8d : pan/bi: Lower depth/stencil stores
6433fedcf1c : pan/bi: Emit +ZS_EMIT as needed
0c889e76112 : pan/bi: Stub handling for nir_intrinsic_store_combined_output_pan
f67b49d5123 : pan/bi: Factor out bi_emit_blend
928f2bc0d57 : pan/bi: Factor out bi_emit_atest
f14beeb4cee : pan/bi: Infer z/stencil flags from sources passed
2b1db3662f3 : pan/bi: Add +ZS_EMIT instruction to IR
cd66aa712d9 : panfrost: Deduplicate shader properties
4a2ecc72d34 : panfrost: Pass through src_type
42319c56264 : pan/mdg: Move writeout lowering to common panfrost
dfaa4c51fba : pan/mdg: Deduplicate nir_find_variable_with_driver_location
a05921b9f21 : nir: Add SRC_TYPE to store_combined_output_pan
fa869fb9b45 : v3dv: add a v3dv_bo_init helper
456beb40b8f : aco/ra: Fix counting of subdword variables in get_reg_create_vector
786828131a7 : aco: implement 8/16-bit instructions which can be trivially widened
ef95ba8cdd1 : aco: implement some 16-bit arithmetic instead of lowering
8ed7cad75f3 : radv: rework nir_lower_bit_size callback and run DA on GFX8+
b2ce7da1498 : radv: do nir_lower_bit_size after algebraic optimizations
c77114967f8 : radv: move a few passes to after load/store vectorization
475077c790f : nir/lower_bit_size: optimize upcast of b2i8/b2i16
4e5c85526b1 : nir: add shader_info::bit_sizes_used
7d3df69914d : va: support VA_RT_FORMAT_PROTECTED
81be8b3c2f2 : va/picture: make sure destination buffer is protected if needed
70191f38e32 : frontends/va: Added protected playback support for VP9
f20a20b1e3f : radeon/vcn: program drm message buffer
ebbf40fa263 : radeon/vcn: delay dec->ctx and dec->dpb allocation
cf324df6eae : radeon: add si_vid_create_tmz_buffer helper
024be710a72 : radeon/vcn: add defines for drm message buffer
b9753fdc581 : radeon: add decryption params definition header
deb7dc82f62 : frontends/va: handle protected slice data buffer
5f0816eac09 : vl: add flag and definition for protected playback
58e7088628a : nir/find_array_copies: Don't assume all children exist
e1736c7fdb2 : radesonsi: Remove unnecessary shader->selector NULL check.
5fb77a582a8 : lavapipe: request correct sample mask behaviour
47701d47e79 : llvmpipe: respect the sample mask in non-multisample flag
3dc6da1ac1f : gallium: add a non-multisample sample mask out behaviour flag.
4ff4d4e5696 : nir/opt_intrinsic: Optimize bcsel(b, shuffle(x, i), shuffle(x, j))
2f5b56ae237 : nir/opt_intrinsics: Refactor a bit
3b281861c1a : nir/constant_folding: Fold subgroup shuffle intrinsics
e59d6350d1f : nir: Move constant folding of vote to opt_constant_folding
9492ab28640 : nir/constant_folding: Use the standard variable naming convention
9d2ccbfc15c : nir/constant_folding: Use a switch in try_fold_intrinsic
d9c0f3627d7 : nir/opt_intrinsics: Report progress for the gl_SampleMask optimization
b90063201a9 : nir: use nir_alu_src_is_trivial_ssa() in nir_ssa_for_alu_src()
233a820f2c3 : nir: skip bcsel with non-trivial swizzle in opt_simplify_bcsel_of_phi()
1df2fc9f9c8 : nir: add nir_alu_src_is_trivial_ssa()
b9f95280119 : nir/lower_io: Add a new 62bit_generic address format
b84f74f9b7f : nir/lower_io: Support generic pointer access
a451f037ffc : nir/lower_io: Add support for lowering deref_mode_is
57943112d9a : nir/lower_io: Add support for 32/64bit_global for shared
c50332fbc29 : nir/lower_io: Add a mode parameter to addr_format_is_*
7007d06898a : nir/lower_io: Add a mode parameter to build_addr_iadd
ff838abc463 : nir/opt_deref: Add an optimization for deref_mode_is
df51518dc5b : nir/opt_deref: Add a deref mode specialization optimization
a8e53a772f6 : spirv: Add generic pointer support
d6415b5d2b3 : nir: Add support for generic pointers
9d377c01d0f : nir: Make nir_deref_instr::mode a bitfield
7d5f3b5c0e6 : nir/split_*_vars: Prepare for generic pointers
d50a4dbc13c : nir/find_array_copies: Prepare for generic pointers
ced9b6f0d8e : nir: Use nir_deref_mode_may_be in deref optimizations
379d5354804 : nir/vec3_to_vec4: Use nir_deref_must_be
8a2cda1d53f : nir/vars_to_ssa: Use nir_deref_must_be
0f94ff8a6ac : nir: Only force loop unrolling if we know it's a in/out/temp
fff78fc1c58 : nir/phis_to_scalar,gcm: Use nir_deref_mode_may_be
9f3e3dfd2fb : nir/lower_io: Use nir_deref_mode_* helpers
9ae87a6c312 : nir/lower_array_deref_of_vec: Use nir_deref_mode_must_be
3cc58e64706 : nir: Add and use some deref mode helpers
74886cabaa3 : nir/opt_find_array_copies: Allow copies from mem_constant
89abfbeb7ac : nir: Disallow writes to system values and mem_constant
bb5d5029b74 : nir: Use var->data.mode instead of deref->mode in a few cases
5664713d7b9 : nir: Handle incomplete derefs in split_struct_vars
6b72004f12c : nir/phis_to_scalar: Use a deny-list for load_deref modes
3f0a29fffbc : nir/builder: Add a nir_ieq_imm helper
9d3615166ef : lavapipe: don't advertise linear filtering on integer textures.
3d81cf4621e : lavapipe: use clear_buffer callback
c3d8a69c3a6 : llvmpipe: add clear_buffer callback. (v2)
1e3fbee4b0a : lavapipe: stop crashes with 3D z blits
c871ac04a15 : lavapipe: fix 3d compressed texture copies.
42b5cfdbd26 : gallivm/nir: fix vulkan vertex inputs
621c4f816f1 : gallivm/nir: handle dvec3/4 inputs properly.
a5aab63fb10 : lavapipe: fix dEQP-VK.info.device_properties
6dabb8065ab : lavapipe: constify state pointers into command buffers.
33a2f27ce96 : lavapipe: don't write to pending clear aspects in cmd buffer
ad3849259a8 : gallivm: fix f16 quantize.
7ae81d65a49 : r600: amend space check for chips older than EVERGREEN
902b3182133 : zink: break up dynamic access lowering
e12e67476a5 : zink: add pass for lowering dynamic ubo/ssbo block indexing to constants
71a197943cf : mesa/st: Fix a use-after-free of the NIR shader stage.
6b85a887ff5 : mesa/spirv: Lower variable initializers for global variables
c2cb2dd3bc6 : zink: Added support for MacOS MoltenVK APIs.
a0f889bdadb : zink: Basic framework to check for optional instance layers and instance extensions.
bfa9fd88fc7 : radv,radv/winsys: Move RADV_MAX_IBS_PER_SUBMIT
f6e5baf4afe : docs/features: add some extensions we missed
a2056b025ce : docs/features: VK_KHR_mir_surface is disabled, remove it
3d58ab7576d : docs/features: Minor update extensions support
89c4bba8bce : nir/algebraic: better propagate constants up fadd chains
16c756e55d5 : spirv: reverse order in matrix multiplication
24a18b1a4b9 : nir: scalarize fdot in reverse
6dc6b8ad9f2 : panfrost: Set .array_size on Bifrost
eaf0be88f6c : pan/bi: Don't emit TEXS for array textures
3a86e1e92d9 : pan/bi: Handle 3D/array coordinates
56bda0fb494 : pan/bi: Track tex data register swizzles
1463824319b : panfrost: Add bi_emit_array_index helper
914eebb0bce : panfrost: Drop unused swizzles
b6c71425c26 : panfrost: Advertise Bifrost support
828c7e76267 : panfrost: Disable point sprites on Bifrost
2ed003633cd : pan/bi: Lower +CUBEFACE2
31864017510 : pan/bi: Suppress disassembly for internal shaders
2f00f82469e : pan/bi: Lower cube map coordinates
f76558be656 : pan/bi: Hook up cube instructions packing
0ed8eee7069 : pan/bi: Split special class in two
20cc63815cd : pan/bi: Move special instruction packing to a separate helper
07f1df51aa3 : pan/bi: s/t0/t1/ in bi_disasm_dest_add()
47131919d86 : panfrost: Implement v7 texture payloads
4e0826dcc85 : panfrost: Add array size to XML
557633b142e : panfrost: Suppress Bifrost prefetching
c0b8f7394bc : panfrost: Leave push_constants pointer to NULL if there's no uniform
29fc115d581 : mesa: do not throw _mesa_problem when invalid enum is used
e02e1ccbeed : mesa/st: call memobj_destroy only if there is memory imported
57c152af9ce : aco: select v_mul_{hi}_u32_u24 for 24-bit multiplications
3a72021d7cf : aco: store NIR range analysis data to the isel context
81ff38947a4 : zink: clamped maxPerStageDescriptorUniformBuffers limits to INT_MAX when stored as uint32_t.
ac65d3b6b85 : radv: fix shader caching with NaN fixup workaround
36f62494ec7 : radv: fix shader caching with discard->demote workaround
19f3911cf82 : radv: add some missing radv_{start,stop}_feedback
200bcd7a44d : android: freedreno: Add freedreno_dev_info.[ch] to Makefile.sources
09b2bd1df93 : broadcom/compiler: remove v3d_fs_key depth_enabled field.
21ffacff8c7 : intel/compiler: remove branch weight heuristic
06764e0e5d5 : intel/compiler: use C++ template instead of preprocessor
788f6dc8578 : Revert "gallium/dri: fix dri2_from_planar for multiplanar images"
fe3e571870e : tu: Support rasterizerDiscardEnable and RasterizationStreamSelect
841f7368243 : tu: Support geometryStreams
6b8d30ec1e3 : util/bitset: Add a range iterator helper
563789ce372 : ir3: Support geometry streams
48cfaecd4f3 : freedreno/a6xx: Update SO registers for streams
92022f2846e : zink: add VK_STRUCTURE_TYPE_WSI_MEMORY_ALLOCATE_INFO_MESA for WSI allocations
98ebffc9f30 : etnaviv: move etna_destroy_shader(..) to generic location
2dc73d2c7f7 : etnaviv: move etna_dump_shader(..) to generic location
3bef6dfe422 : etnaviv: convert from tgsi semantic/index to varying-slot
edbdd977232 : nir: make tgsi_varying_semantic_to_slot(..) public
4bd18e772a2 : amd/llvm,aco: Replace VLA with alloca
e3515590bfb : zink: require Vulkan timestamp queries for time query caps
b07b943f30c : tgsi: Initialize tgsi_declaration_dimension padding.
7278f900394 : gallium: Remove duplicate resource variable.
78a420ce467 : nir/validate: Explain why we don't use nir_foreach_block
e8a332b972e : zink: always reset query pools on next query begin
60db5af05a7 : zink: always use query->type for starting/stopping xfb queries
e1e3484a10b : zink: rework query overflow handling
7fc806bbbc9 : zink: fixup gs/xfb tracking for primitives generated queries
28ad3c1735a : zink: store batch id onto query object at time of start
b073398be1d : zink: also create an xfb query for every primitives generated query
0b2475f5fd1 : zink: more correctly handle PIPE_QUERY_PRIMITIVES_GENERATED queries
a8785579e00 : zink: deduplicate some query result code
b6a0309f482 : lavapipe: use resource get param.
2dcc9c7f54e : llvmpipe: add resource get param support.
ae17e1fdbcb : gallium: add a layer stride pipe resource parameter.
e9724722a3a : gallium: add a level parameter to resource parameter get
0e3f2e63215 : zink: call the reset callback not only during a status check
efadeb3269b : i965: remove prototypes of not-existing functions
e3f6a9ea36d : intel: remove dead code
b5e2c58ad86 : anv: always annotate memory returned from anv_gem_mmap
990343b70da : turnip: rework android gralloc path so it doesn't call tu_image_create
b2a21febe04 : os: Fix open result check.
1eda8423187 : iris/bufmgr: Handle NULL bufmgr in iris_bufmgr_get_for_fd
eb61f8959e0 : i965/bufmgr: Handle NULL bufmgr in brw_bufmgr_get_for_fd
aa2f6bd4f56 : freedreno: Use freedreno_dev_info
a1d2b215f10 : tu: Use freedreno_dev_info
4a0bdf47e43 : freedreno: Introduce common device info struct
ea81889ea43 : nir/large_constants: only search for constant duplicates
ce5e2e21317 : nir: Stabilize compact_components sort
aaa94d92d52 : docs/features: add Vulkan 1.2
8c4d15d57ee : docs/features: update unpromoted Vulkan extensions
8077f3f4c4a : nir/lower_returns: Append missing phis' sources after "break" insertion
95b9fc41466 : zink: implement pipe_device_reset_callback
7d6609e70d5 : v3dv: fix occlusion query inheritance in secondary command buffers
12f87b6e7c3 : v3dv: add support for timestamp queries
520f3e27b5b : radeonsi: fix RADEON_FLUSH flags conflicts
18b7cafc700 : driconf: add disable_protected_content_check option
9b0ffa9ecde : egl/dri2: implement createImageFromDmaBufs3
d9582ff39e0 : dri: introduce createImageFromDmaBufs3
2aff88a9457 : egl: handle EGL_PROTECTED_CONTENT_EXT for eglImage
52268a3833e : radeonsi: enable PIPE_CAP_DEVICE_PROTECTED_CONTENT
bd182777c8f : egl: implement EGL_EXT_protected_surface support
9698a222a6c : radeonsi: honor PIPE_BIND_PROTECTED
a6535045499 : gallium: introduce PIPE_BIND_PROTECTED
7748e501382 : gallium: add new cap PIPE_CAP_DEVICE_PROTECTED_CONTENT
b54c054a418 : v3dv: expose VK_KHR_maintenance1
53c6dc504b0 : v3dv: implement vkTrimCommandPool
0dedee7636e : v3dv: update assertion to match VK_KHR_maintenance1 semantics
e4988e6affe : v3dv: fix base slice selection for copies involving 3D images
0a9b8077adb : v3dv: add image view debug checks for VK_KHR_maintenance1
03f260cb272 : radv,aco: optimize computing the sample mask for per-sample shading
c63bcda22c8 : radv,aco: adjust the sample mask only if per-sample shading is enabled
ea83fd91242 : glsl: drop NMS OpenGL workarounds
d5dd779c490 : panfrost: Add missing alpha-first special formats
3a67806edcd : panfrost: Fix BGR233 component order
b5bc0935841 : panfrost: Fix RGB5A1 formats
f2af23bd120 : panfrost: Use macro for panfrost_get_default_swizzle
c5d86198a4e : panfrost: Add missing 1/2/4/64-bit formats to XML
d473622fdee : panfrost: Rename VARYING_POS to SNAP4
1b5cac4511f : panfrost: Rename VARYING_DISCARD to CONSTANT
c6bdd976e61 : panfrost: Split out v6/v7 format tables
29bb2812c14 : panfrost: Add v7-specific depth formats
8ca1478b2b3 : panfrost: Add miscellaneous missing Midgard formats
a21d3debc3f : panfrost: Add missing depth/stencil formats
f6fb9ef919f : panfrost: Add v7 special colour formats
cae1be954ca : panfrost: Remove panfrost_is_z24s8_variant
870283bcc4a : panfrost: Remove duplicated format arg for ASTC
44155fa661c : panfrost: Complete format_to_bifrost_blend
e1624b67dc1 : panfrost: Use panfrost_blendable_formats for blending
41f06ac8776 : panfrost: Use panfrost_blendable_formats for SFBD
293198ea04e : panfrost: Use panfrost_blendable_formats for MFBD
d9b16ca4c91 : panfrost: Add a blendable format table
666677d0ef5 : panfrost: Use consistent swizzle names in XML
1e18d9952bb : panfrost: Add MALI_EXTRACT_INDEX helper
1b48b9e6190 : panfrost: Don't double-compose swizzles
a575bb13697 : draw: Remove draw_install_aaline_stage dead code.
0a4c1db926c : gallium/u_threaded: merge consecutive draw calls within batches
d0916ccb109 : gallium/u_threaded: move a structure up to be used later
a44868beda5 : radeonsi: implement multi_draw for compute-based primitive culling
cc24ec8c077 : radeonsi: set NOT_EOP for back-to-back draws on gfx10+
ca40dc01cc8 : radeonsi: add support for multi draws
0ce68852c1a : radeonsi: implement multi_draw but supporting only 1 draw
ae8d89260c6 : radeonsi: don't check info->count == 0
d9c4ca2b7bc : radeonsi don't get count from pipe_draw_info in si_num_prims_for_vertices
7cc939f7dde : radeonsi: add num_draws parameter into si_need_gfx_cs_space
095ee8f867b : winsys/amdgpu: remove incorrect assertion check against max_check_space_size
73f2d3c291f : gallium: add pipe_context::multi_draw
d9c12c60723 : gallium: move pipe_draw_info::start/count to the beginning and pad empty space
8943c80c9b1 : radv: Fix variable name collision.
41be85ad7bc : ci/x86: speed up piglit testing
e54c7f4b1ac : android: aco: add aco_form_hard_clauses.cpp to Makefile.sources
a1d6c03e2f3 : etnaviv: don't import allocated scanout resources via from_handle
3862cec314d : etnaviv: pass correct layout to etna_resource_alloc for scanout resources
ec21148311f : etnaviv: simplify etna_screen_bo_from_handle
94ec412b268 : etnaviv: do proper cpu prep/fini when clearing allocated buffer
181790117bd : etnaviv: cosmetic etna_resource_alloc fixes
98db7c4841c : etnaviv: free tgsi tokens when shader state is deleted
3fd512440bf : etnaviv: tex_desc: fix TS compression enable
cf871e92327 : etnaviv: update headers from rnndb
3ba753d9f58 : etnaviv: blt: properly program surface TS offset for clears
866bb22d6b9 : etnaviv: drm: fix BO refcount race
8b0218beb59 : etnaviv: drop etna_pipe_wait(..)
b7501184b90 : radeonsi: implement inlinable uniforms
6d058ac6c99 : aco: Fix accidental copies, attempt two
b03c86a71f3 : intel/dev: Bump Max EU per subslice/dualsubslice
5957b0c1622 : glthread: pin driver threads to the same L3 as the main thread regularly
d8ea5099658 : util: completely rewrite and do AMD Zen L3 cache pinning correctly
4f2c2307f9e : util: add util_get_current_cpu using sched_getcpu and Windows equivalent
9758b1d416a : util: add util_set_thread_affinity helpers including Windows support
3433d193e7c : st/mesa: remove random L3 pinning heuristic for glthread
96d9f7761d4 : util: consolidate thread_get_time functions
53a15925da5 : util: remove unused util_get_L3_for_pinned_thread
cc161132027 : android: fix libsync dependencies (v2)
a09717c4de0 : glsl: add extra pp tokens workaround and enable for CoR
ce0b72a13a2 : intel/fs: Don't emit_uniformize when getting a constant SSBO index
0fe5490724e : v3d/format: use XYZ1 swizzle for three-component formats
f7d1460418f : gallivm: zero init the temporary register storage.
17613794815 : aco: handle SDWA in the optimizer
ecc5b59a706 : aco: don't allow destination opsel for v_cvt_pknorm
bb890f2e7c1 : aco: fix combine_inverse_comparison()
7e4aa8c8e9b : aco: fix printing of some sdwa sels
70320f41172 : aco: assert a label only uses one of the members in ssa_info's union
3dfbed2a87c : aco: create s_clause on GFX10+
f4c090a3b3c : aco: refactor split_store_data() to always split into evenly sized elements
daec83c7d61 : intel/genxml: don't generate identical code for different branches
e96f33cd300 : intel/tools: fix invalid type in argument to printf
13859c769f0 : gallium/dri: fix dri2_from_planar for multiplanar images
6c118aebb11 : gallium/dri: fix dri2_query_image for multiplanar images
0f3594cd7b0 : gallium/dri: allow create image for formats that only support SV or RT binding
25f984812be : nv50/ir/nir: don't use designated initializers
e07c5467633 : v3dv/format: use XYZ1 swizzle for three-component formats
d8562b742ea : virgl: Correctly align size of blobs
7dc17ae5abc : glsl: Update loop_terminator constructor to accept parameters.
f74ef158798 : aco/ngg: Incorporate GS invocations into workgroup size calculation.
09b9e52c0d8 : aco/ngg: Export a zero-area triangle when primitive count is 0.
73449f9a623 : aco: Add a few assertions about LDS usage.
b6654adc0ea : aco: Make emitting reduction instructions a bit more convenient.
8d6246205ad : aco: Add some validation for PSEUDO_REDUCTION instructions.
260f9c503ad : aco/ngg: Put shader query reduction operand into a VGPR.
9757c3cb6b8 : aco: Assert that workgroup barriers are not used inappropriately.
915f2919f64 : ci/bare-metal: suppress 'No such file or directory'
ecdcf22d5d8 : aco: switch aco_print_asm to a FILE *
a293fad4ef7 : aco: refactor repeated instruction disassembly
ed2449d55be : aco: move individual instruction disassembly to its own helper
7ded846ba92 : docs/features: Update extensions for swr
2088f359ff8 : docs/features: Update extensions for softpipe
483657de323 : aco: use mubuf helper in select_gs_copy_shader
ec7ecfe9cbf : aco: use control flow creation helpers in select_gs_copy_shader
57d977a23fb : aco: round bytes_written to dwords if larger than 4 bytes
41839d38cf3 : aco: default to a definition size of 32
768186e2af3 : docs: s3tc -> S3TC
d30470e999b : docs: clang -> Clang
f3095f9b40c : docs: gcc -> GCC
4aded097346 : docs: fbo -> FBO
e8d0313df54 : docs: hud -> HUD
f408343198a : docs: api -> API
a22cedf4f0f : docs: anistropy -> anisotropy
689145eeb2b : docs: eg. -> e.g.
580b9d11ff2 : docs: ie. -> i.e.
fef8a4befdc : radv: remove call to nir_lower_pack()
212be2a04e4 : radv: lower pack_[64/32]_* via nir_lower_alu_to_scalar()
bd0468ed338 : nir: add options to lower nir_op_pack_[64/32]_* via nir_lower_alu_to_scalar()
121fa017e1d : ac/nir: implement nir_op_[un]pack_64_4x16
543f50789a4 : aco: implement nir_op_unpack_[64/32]_*
79cd22b889b : v3dv: enable alphaToOne feature
eb104e949ee : radv: Do not access set layout during vkCmdBindDescriptorSets.
29999e6b9d7 : radv: Fix 1D compressed mipmaps on GFX9.
06cf838cbdc : intel/mi_builder: Support gen11 command-streamer based register offsets
fdb1997ab5e : Fix VMware capitalization.
0e7d45c89a5 : util: use dllexport for mingw too
e030ab51632 : lavapipe: configure suffix in icd json
3017d884bc0 : gallium: use libpipe_loader_links
0355d10c6bd : wsi: move drm code to wsi_common_drm.c
72ce22f9918 : lavapipe: fix usleep usage in lvp_device
d399c3e861a : intel/dev: Add device info for ADL-S
26e53e3afa7 : aco: ignore the ACO-inserted continue in create_continue_phis()
fa5acbbcdea : CI: remove llvmpipe cl flake test
8d03cfae7c3 : anv: Drop warning about gen12 not being supported
a1885332d76 : panfrost: AFBC compress Z16 depth buffers
388c99b0298 : panfrost: Z16 depth buffer support
4a20ed6b45a : panfrost: Move zs format handling code out of the !afbc case
06d1f7c64b2 : docs: Specify when branch points happen
328a3503875 : vulkan/util,vulkan/wsi,radv: Add typed outarray API
437995bb705 : aco: remove all-undef phi opt
70ff262cda8 : aco: use v_mov_b32_sdwa for some 16-bit constants
b882598ee17 : aco: remove some unused optimizations
d20a752c0de : aco: use Builder::copy more
e54c111c459 : aco: always use p_parallelcopy for pre-RA copies
6db5fbf9f27 : aco: allow literals on sub-dword p_parallelcopy
74e2e9b682a : aco: don't use bld.copy() in handle_operands()
a834d9ef86a : aco: expand vectors passed as copy operands
e092f34dfa3 : aco: copy-propgate through p_create_vector during value numbering
0f31fa1b645 : aco: skip value numbering of copies
72b307a3389 : aco: don't do divergent break+discard
d4503a90205 : aco: update phi_map in add_subdword_operand()
23fb54bf7fa : aco: Clean up some C++ usages
79347f5cd45 : radv: enable VK_AMD_mixed_attachment_samples on GFX6-GFX7
ee1d30ab8a9 : radv: flush CB before and after FMASK_DECOMPRESS or DCC_DECOMPRESS
3fee91d2e7e : docs: add link to extension spec
76f74bd653e : CI: Only run OpenCL tests when we need to
48e83f76653 : radv: do not perform a FMASK expand for non-writeable MSAA images
cb12879401b : aco: fix GFX8 16-bit packing
666817ce846 : v3dv: grow meta descriptor pool dynamically
6b874eb42c8 : ci: Run git_archive job if all_paths matches
e5cd5e9cec9 : pan/mdg: fix LOCAL_STORAGE wls_instances packing
e4b170a7206 : v3dv: enable the logicOp feature
af0435cbfe6 : Revert "radeonsi: use staging buffer uploads for most VRAM buffers"
e29fb8e80f1 : amd/addrlib: Initialize Gfx10Lib members in constructor.
006ce7358c1 : freedreno/gmem: Respect max-height limits too
9f5c8ff0ae8 : freedreno: Rework GMEM limit init
6c6693e043a : pan/bi: Fix ms_idx type to catch missing ms_index source
eaed477652a : pan/bi: Add ult support
f77bbc92364 : pan/bi: Lower {i,u}{min,max} instructions
1c8b8e3c82e : pan/bi: Add support for load_point_coord
55c0dd943e9 : pan/bi: Add support for load_front_face
0a582b53f22 : panfrost: Preload primitive flags when gl_FrontFacing is accessed
b92eadb29cc : ci: Add "check mr" job to needs: of build jobs
27ce5d921ef : aco: remove isel_context::allocated
6f68cacf619 : virgl: Always enable emulated BGRA and swizzling unless specifically told not to
3d9ffdcc729 : nir/lower_memcpy: Don't mask the store
67238f95b52 : freedreno: Disallow tiled if SHARED and not QCOM_COMPRESSED
63bdbfd045d : freedreno: Update import/export traces
5f686c308ab : st/va: fix build with old libva
638ebdea78e : glx: get rid of memory leak
26f58e87a0d : mapi: do not return thread-specific data for wrong thread
61d40ae4d04 : mapi: do not call thread-unsafe dispatch getter
65d6f258c52 : mapi: remove unused function
cf083f1d02b : aco: use do_pack() for self-intersecting operations.
d96f387e7ac : aco: improve code sequences for 16bit packing
40bfb088285 : aco: refactor GFX6_7 subdword copy lowering
06b41ca5899 : iris: add support for fence signal capability
aa1d298b339 : iris: handle PIPE_FD_TYPE_SYNCOBJ type
bddaa9339c7 : ac/nir: remove bindless image atomic format check
2ff97847d19 : docs: document zink's gl > 3.0 requirements
be693beef1e : docs: do not document required minimum
dd0f9410974 : zink: verify geometry shader feature
82512a163ba : gallivm: lower flrp for all sizes.
b8a9bd9b936 : gallivm: get correct min/max behaviour for kernels.
9845c1636cc : gallivm: add support for 8/16-bit mul_hi
4b6d3328432 : gallivm: handle sub-32 bit masked stores.
81d8ca70eb0 : gallivm: add b2i8/b216 support
0f78ca9d546 : gallivm: add 16-bit split/merge support.
4ecdc5ec4e2 : gallivm: fix 64->16 f2f16
842a53913c0 : llvmpipe: fix 8/16 bit global stores
d1ea49d9244 : anv: report latest extension spec versions
303a74c52c0 : android: panfrost: Move nir_undef_to_zero to util
6a189c89f8b : util/xmlconfig: Disable for Windows like Android
fb56fb02a1e : gallivm: add load/store scratch support.
9c1f6ed8044 : frontends/va: Initialize drm modifier on import.
bef6007c3aa : gallium: update abs_delta segementation parameter
9c67f3d723a : frontends/omx/enc: fix omx h264 encoding force-keyframe-period issue.
390887ff586 : mesa: Remove the key parameter from the _mesa_HashDeleteAll callback
cc6dcc6ab4f : mesa: Remove the key parameter from the _mesa_HashWalk callback
ca752b08c90 : i965: Get the gl_perf_query_object Id from the object
f71488d1d10 : mesa: Store the atlas Id in the gl_bitmap_atlas structure
0e17bb509e6 : mesa: Open-code hash walk in _mesa_HashPrint
3c2489d2e45 : amd: print NUM_PKRS with AMD_DEBUG=info on gfx10.3
989cc76f0c9 : amd: replace 0x028848 with the register definition
e72b76b94bd : amd: update gfx10-rsrc.json for gfx10.3
e477255271a : amd: correct typos in gfx10-rsrc.json
19e32793b61 : amd: regenerate gfx103.json from kernel headers
9d3b802c6a9 : scons/windows: Support build with LLVM 11.
f21dd3bc5a0 : scons: gallium/auxiliary: Unconditionally compile NIR regardless of LLVM
3ba786f6243 : spirv: Fix OpCopyMemorySized
a071590b1d1 : frontends/omx/h265: Check the pps set before the scaling data
08762d5171b : frontends/omx/dec: Use the known codec profile when allocating buffers
56f90a6ac19 : pan/bi: Account for bool32 ld_ubo reads
3cdca1514f6 : panfrost: Don't advertise MSAA on Bifrost
f0e65805cb8 : panfrost: Drop PIPE_CAP_GLSL_FEATURE_LEVEL for Bifrost
b9a136cdd1e : panfrost: Implement BGRA textures
048e4315426 : panfrost: Fix component order XML
25b66e61f73 : panfrost: Calculate thread count on Bifrost
fb32406e566 : panfrost: Don't export queries
f4ecc432bf7 : panfrost: Record architecture major version
81b28ebcb5a : pan/bi: Use nir_undef_to_zero
86b2b4eb768 : panfrost: Move nir_undef_to_zero to common util/
f0421099efc : pan/bi: Pipe through tls_size
b43b1535e25 : pan/bi: Implement spilling
e33b2976f3a : pan/bi: Pack LOAD/STORE
74be83d876f : pan/bi: Add bi_foreach_clause_in_block_safe helper
2ff54cacf0e : pan/bi: Factor out singleton construction from scheduler
2d0f46a181b : pan/bi: Implement bi_spill_register
82dbc4ea782 : pan/bi: Add helpers for working with singletons
1db83fc75d9 : pan/bi: Add bi_rewrite_index_src_single helper
9e915fd5f74 : pan/bi: Add bi_fill
486a820bc67 : pan/bi: Add bi_spill helper
171bf199171 : pan/bi: Add spills/fills parameters
7246dd88cda : pan/bi: Implement bi_choose_spill_node
ab9abc9052f : pan/bi: Add no_spill flag to IR
ad8a8499c9b : pan/bi: Stub spilling
8477678cfeb : pan/bi: Fix handling of small constants in bi_lookup_constant
82a62a6f331 : pan/bi: Drop 64-bit constant support
d2bfcba54d8 : pan/mdg: Cleanup mir_rewrite_index_src_single
b19d9c86a87 : panfrost: Drop panfrost_vt_emit_shared_memory
e6152091ca9 : panfrost: Use canonical characterization of tls_size
a33827d3d31 : panfrost: Get rid of the non-native wallpering bits
c89f659f03f : panfrost: Use native wallpapering on Bifrost
edd98aac3f1 : panfrost: Add support for native wallpapering on Bifrost
a677e34e1fc : panfrost: Split panfrost_load_midg()
8892c9cde1b : panfrost: Pass the texture payload through a panfrost_ptr
3f91d819450 : panfrost: Rename gtransfer to transfer
1b3b289c5c1 : panfrost: Rename panfrost_transfer to panfrost_ptr
bf3cd28319c : panfrost: Use real name for attribute's unknown field
6b68c821d11 : panfrost: Build blit shaders on Bifrost too
69c864b0b92 : panfrost: Make {midgard,bifrost}_compile_shader_nir() return a program object
b83c293674c : pan/bi: Add basic support for txf_ms
d33c8afe9b5 : pan/bi: Support the case where TEXC needs 0 or 1 staging reg
4aff27a68a1 : pan/bi: Add support for load_sample_id
e2d61567422 : pan/bi: Print blend descriptor source properly
74c158011d0 : pan/bi: Make sure we don't print special index as a register
a194dcc827e : panfrost: Replace unkown renderer state fields by their real names
7486b5d91ee : panfrost: Add specialized preload descriptors
d769697f35c : panfrost: Add the bifrost tiler internal state field
2f1947b39ca : panfrost: Fix tiler job injection
519643bbe0c : panfrost: Adjust the renderer state definition
f2ae8d116ab : freedreno/a6xx: Implement user clip/cull distances
b4224c39e12 : tu: Implement clip/cull distances
47f825ac636 : ir3: Handle clip+cull distances
9e063b01b77 : ir3: Switch tess lowering to use location
4ca38a19957 : nir/lower_clip_cull: Store array size for FS inputs
cb6ce4a265b : iris: fix the order of src and dst for fence memcpy
d972a6ac4c8 : nir: get rid of OOB dereferences in nir_lower_io_arrays_to_elements
33c9d4bf315 : radv: replace RADV_TRACE_FILE by RADV_DEBUG=hang
9516f9369e4 : radv: re-order GPU hang report dumps by usefulness
719b9b3e27e : radv: dump GPU hang report logs into $HOME/radv_dumps_<pid>
ef6d374307b : radv: dump UMR ring and waves into the hang report
18477241c1d : radv: add radv_dump_cmd() helper
bf66bbda809 : ac: add an option to dump GPU info to a file
5f16c5b6f96 : v3dv: properly describe swap_color_rb
d8cabe0cbe2 : v3dv: compute swap_rb flag after applying all swizzles
40788be1343 : v3d/compiler: fix BGRA vertex attributes for vec2/float size.
c15468d782b : broadcom/cle: fix vec size dump when set to 0
53fc3eb4a22 : glsl: Initialize lower_shared_reference_visitor members.
0eccd15852b : frontends/va: Return P010/P016 as possible surface formats when encoding
b50f40fa5a9 : src/util/disk_cache_os.c: Add missing headers for open/fcntl
ddca93ddf70 : anv: Enable stencil buffer compression on Gen12+
dc22d6b3ab1 : anv: Pass correct stencil aux usage during MSAA resolve
993a2a71224 : anv: Return optimal aux state for stencil buffer compression
815e6c8ef4e : anv: Don't track clear bo for stencil buffer compression
d34ab5071a8 : anv: Get aux usage from plane while clearing stencil buffer
c76ebc0c7a6 : anv: Set stencil_aux_usage flag
be2ca24da55 : anv: Handle compressed stencil buffer transition on Gen12+
c2a41028485 : anv: Return number of layers/levels attached to anv_image
67956689bb8 : nir: Rename replicated-result dot-product instructions
8cee9ce750e : spirv: switch to util_bswap32 to improve portability
7e28fbd8bc5 : ci: Add the new timeout-prone softpipe-gl test to the skips list.
18cef9c5149 : docs: Fix "Hosted by" link and drop duplicate.
1dd6495f78c : docs: Add a link to the linux kernel DRM docs under "Developer Topics"
2f39dac6e89 : docs: Drop extra link to old DRI wiki in the "Help" section.
31e9de9c8ac : loader/dri3: Allocate up to 4 back buffers for page flips
16a7cc4d449 : loader/dri3: Keep current number of back buffers if frame was skipped
60585fc4e34 : loader/dri3: Only allocate additional buffers if needed
ea326912575 : anv: fix source/destination layers for 3D blits
87934f02f9d : blorp: allow blits with floating point source layers
e067078fcd2 : blorp: identify copy kernels in NIR
6694b4276b8 : ac/nir: abort when an unknown intrinsic is reached
fa490cb6ac3 : ac/nir: ignore set_vertex_and_primitive_count intrinsic
b739bb71680 : compile/nir: Correct printing dest_type
4e2fe34aa99 : aco: fix determining if LOD is zero for nir_texop_txf/nir_texop_txs
4735c8a522c : nir/loop_analyze: adjust force unrolling to only include interesting modes
542feb9ab6f : ci: disable check commits job for now
8f9c5964ab3 : v3dv: handle buffer to linear depth/stencil image copies in blit path
61b8a49e86d : v3dv: handle compressed image to buffer copies on the blit path
462429b4b8b : v3dv: fix Z coordinate for 3D blits
a18411d9c60 : v3dv: do not attempt to blit from a linear image source
2118c9b562d : v3dv: fix multi-layered buffer to image copies on the blit path
0a4fc196058 : v3dv: skip unnecessary tile loads when blitting
c83d6ffa322 : gallivm/nir: handle nir_op_flt in lp_build_nir_llvm
91b64da3de5 : driconf: allow higher compat version for Brink
edd0b00c2be : driconf: disable GLX_OML_swap_method by default on Brink
d2cb3f862f2 : driconf: add a way to override indirect-GL extensions
7eedc79658d : driconf: add a way to override GLX extensions
97f6d5e3a99 : glx: let users force-enable/disable indirect GL extensions
e19644967f2 : glx: initial plumbing to let users force-enable/disable extensions
74722c3ab91 : glx: rework __glXCalculateUsableExtensions to be more readable
1331b86299b : glx: stop using hardcoded array sizes for bitfields
af25f47bdce : glx/extensions: split set_glx_extension into find_ and set_
4ba255dfaaf : dri/DRI2ConfigQueryExtension: add support for string options
f9763b20542 : driconf: initialize the option value before using it
0e3a424f002 : driconf: bump the maximum string size from 25 to 1024
81797fc863c : android: util,ac,aco,radv: Cross-platform memstream API
025050bae73 : glsl: Initialize ir_if_to_cond_assign_visitor members in constructor.
8cf00244328 : nir: Use a switch in nir_lower_explicit_io_instr
8033200560f : docs/v3d: Add a little stub of v3d documentation.
97dd039191d : docs/vc4: Add information on the hw documentation available.
c4290a52ddb : docs/vc4: Move my old vc4 wiki's documentation into docs.mesa3d.org.
4a4b854aa02 : docs/vmware: Move the vmware driver docs into the drivers section.
313f951f1bd : docs: Move the gallium driver documentation to the top level.
9a644d70173 : docs: specify redirects in conf.py instead
47f52e83d10 : docs: specify redirects relative to docs-root
7daf953bc0e : docs: verify that targets for relative redirects exist
a85c3189fa7 : docs: create leading directories for redirects
b2c737cf573 : virgl: Fixes portal2 binary name in tweak config
3d51c27de55 : st/mesa: initialize lower alpha func to ALWAYS
33ccf0e9bc5 : nir: drop unused alpha_ref_float
42ee423e3ac : nir: drop support for using load_alpha_ref_float
1404b8b1e5b : vc4: do not report alpha-test as supported
8ad931808e2 : v3d: do not report alpha-test as supported
4c41d1900e5 : ci: Add jobs running ci-fairy checks
7b09d501e45 : ci: Add empty needs: to pages job
9d1d3a89c49 : ci: Move test-docs job to deploy stage
549ae5f8437 : st/mesa: make sure prog->info is up to date for NIR (v2)
1126b5cd2f1 : Revert "st/mesa: don't pass NIR to draw module if IO is lowered"
233520035a0 : nir: consider load_color intrinsics as both inputs and sysval in gathering
c69849ef803 : amd: update addrlib
e6e3d8951ab : glx: Move glXGet{ScreenDriver,DriverConfig} to common code
ce8530d6c92 : glx: Delegate the core of glXGetScreenDriver to the GLX screen vtable
3bb7ebfc750 : glx: move __glXGetUST into the DRI1 code
eb6877d3af3 : radv,aco: fix use of texop_samples_identical in the resolve meta path
eacdad7ea0d : ac/nir: do not sign-extend the result of texop_samples_identical
11d70e7ab96 : docs/features: add v3dv driver
354e375c9cc : frontends/va/postproc: Un-break field flag
fd038132de0 : aco/isel: Miscellaneous cleanups using the new Stage API
34bc9477de1 : aco: Clean up symbol names and comments related to NGG
86c227c10cb : aco: Use strong typing to model SW<->HW stage mappings
fdbc45d1d46 : nir: Only validate in passes that might have changed things.
c54c42321ea : glsl: relax rule on varying matching for shaders older than 4.00
c97e82bab50 : panfrost: Only enable occlusion queries when active
04e955f19bb : panfrost: Precise occlusion query support
584b1070372 : st/mesa: Drop the TGSI paths for drawpixels and use nir-to-tgsi if needed.
57effa342b7 : st/mesa: Drop the TGSI paths for PBOs and use nir-to-tgsi if needed.
da4c4c0e678 : gallium/ntt: Add default compiler options for non-native-NIR drivers.
f5841c343b4 : v3dv: Fix assert using assign instead of compare.
e7ce74497e5 : radv: Advertise VK_KHR_shader_terminate_invocation.
bf955d5f0a3 : amd/llvm: Add VK_KHR_shader_terminate_invocation support.
76421667ecf : aco: Add VK_KHR_shader_terminate_invocation support.
22a6396340c : ci: Enable Werror on meson-arm64-build-test.
b03fdca2e00 : turnip: Add error path handling for descriptor pool init.
d384f3be4c0 : turnip: Handle the error path for tu/drm's vkResetFences().
296468ef1ac : turnip: Handle some error paths in allocating CS space from a command buffer.
9b156ef57bf : freedreno/fdperf: Silence a compiler warning about current counter.
a512e9eecd8 : freedreno/tools: Fix compiler warnings about using sz in the error paths.
91c5bbc128b : freedreno/cffdec: Fix format overflow warning.
e4dba528cad : llvmpipe: enable CL images
cda192dc157 : llvmpipe: fix sampler/image binding for clover.
874371876e2 : nvc0/CL: enable images
ee035c75d42 : nouveau: hide SVM support behing a variable for now as kernel space is broken
1a775b71ca5 : clover/nir: set kernel_image cap
4f24dee22a7 : clover/nir: Add an image lowering pass
5e31fad8c9c : clover/nir: Calculate sizes of images and samplers properly
f6c46e8408b : clover/device: use PIPE_MAX_SHADER_SAMPLER_VIEWS for max_images_read
43a42b6e1d0 : clover: clCreateImage: calculate image row_pitch and slice_pitch when not provided
f2bdb692188 : clover: support custom driver strides
9583ce04db3 : clover: validate image_row_pitch and image_slice_pitch in clEnqueueMapImage
1ff4db19351 : clover: Fix incorrect error check in clGetSupportedImageFormats
3aead7198bc : clover: use pipe_image_view for images instead of set_compute_resources
eb965719abf : compiler/types: Allow images and samplers in get_explicit_type_for_size_align
0021d3ae87a : compiler/types: Assert non-zero alignments in get_explicit_type_for_size_align
ef68f740a67 : nir/lower_io: Assert non-zero power-of-two alignments
589d918a4f9 : spirv: Add 0.5 to integer coordinates for OpImageSampleExplicitLod
2015a109ff2 : anv,iris: Use the data cache for UBO pulls on Gen12+
cdc546ae7fe : iris: Flush caches based on brw_compiler::indirect_ubos_use_sampler
fa483d8cd1b : android: gallium/auxiliary: Deduplicate nir_to_tgsi.c inclusion
0f82c99c4e6 : docs: Document how to build and install Android drivers.
c4f8d421df2 : meson: Don't enable libunwind by in 'auto' mode on Android.
f2a27d72de5 : meson: Don't try to build GLX by default on Android.
e3c330c7b21 : freedreno: Use Android's libsync instead of libdrm's.
81a0f1eca24 : meson: Only require libexpat when a part of the build needs it.
442a7696004 : meson.build: xxf86vm is not needed for -Dglx-direct=false
d0f8fe59091 : softpipe: Switch to using NIR as the shader format from mesa/st.
6444f5702dc : softpipe: Fix buffer overflows in SSBO atomics.
34cc6a804ec : gallium: Add a nir-to-TGSI pass.
d867e7c9748 : nir: Add an option to not lower source mods for f64/u64/i64.
c730feacc0d : nir: Add a call to get a struct describing SSA liveness per instruction.
a206b581578 : nir: Add a block start/end ip to live instr index metadata.
2f5d18403a4 : nir: Replace nir_ssa_def->live_index with nir_instr->index.
b6cb184e86d : nir: Introduce nir_metadata_instr_index for nir_index_instr() being current.
b05c107d744 : ci: Enable NIR_VALIDATE everywhere.
4ca10307745 : radv: move all NIR pass outside of ACO
9aa89b36fc4 : ac/nir: handle non-const offset with txf/txf_ms
e690a1b78bf : ac/llvm: don't lower bool to int32, switch to native i1 bool
ed0eb511d9c : util: Fix rwlock Windows include for MinGW
afeb0c30226 : genxml: drop gen10
6d32fcaaafb : Revert "radv/aco: disable NGG GS support because it randomly hangs the GPU"
d8435c1628c : aco/ngg: Add assertion to make sure we always know the vertex count.
d9cb9ff4148 : nir: Emit set_vertex_and_primitive_count for inactive streams.
07fae31e8cb : radv: add missing 'discardtodemote' option in the debug list
44081311428 : vulkan/wsi: fix possible random stalls in wsi_display_wait_for_event
85053c016c8 : panfrost: Fix stride for AFBC_FORMAT_MOD_BLOCK_SIZE_32x8.
8dd03a7c125 : anv: Advertise VK_KHR_shader_terminate_invocation
8251eed83e7 : vulkan: Update XML and headers to 1.2.158
7e55f0e17df : clover/nir: add a constant folding pass before lowering mem const
aca31baafc0 : isl: Enable Tigerlake HDC:L1 caches via MOCS in various cases.
02fe825a613 : isl, anv, iris: Add a centralized helper to select MOCS based on usage
103ad427bc7 : anv: Set only one ISL usage bit (RT/texture) for CopyBuffer sources
4df98c3c0ca : turnip: Only link libdrm in the DRM case, not KGSL.
f63ce9bbe0c : turnip: Don't link the WSI code if we don't have a WSI extension.
8f3313fb479 : turnip: Use Mesa's libsync.h instead of libdrm's libsync.h.
8a72666e91b : turnip: Drop a dead error checking path in device init.
27b88879462 : android: Add pre-4.7 Android kernel compatibility to our libsync header.
e8c89a9bcba : util: Import a copy of drm's libsync.h
ab57df26225 : ci/android: Switch build to using platform SDK version 26.
e92f4ac9f46 : android_stub: Update platform headers to include gralloc1.h.
72799886e7e : radv: report latest extension spec versions
cf17d625165 : meson: Add xcb-fixes to loader when using x11 and dri3. Fixes undefined symbol for xcb_xfixes_create_region in loader_dri3_helper.c
25627ffe656 : mesa: Pass the correct caller string to _mesa_lookup_or_create_texture
9b847d4150f : mesa/st: Silence unused parameter warnings in st_context.c
4cd930565e3 : i965: Silence unused parameter warnings
3c87ac1f608 : isl: Fix the aux-map encoding for D24_UNORM_X8
9a062383e35 : anv: Implement VariableDescriptorCount
215218f32f5 : anv: Add a descriptor_count to descriptor sets
dd1971c9d8f : anv: Bump the number of update-after-bind descriptors to 1M
3c0ba7b1802 : zink: reject resource-imports with modifiers
068b4bf76c0 : doc/features: remove zink entries for GL 3.3 items
af8d488ea5e : util,ac,aco,radv: Cross-platform memstream API
4c2e7b08930 : util,radv,radv/winsys: Cross-platform rwlock API
9d4999e7cf7 : anv: Ignore continue flag in primary cmd buffers
b3529e56b5d : ac/nir: implement missing nir_op_pack_half_2x16_split
57d317865e7 : radeonsi: enable NGG culling by default on Navi1x PRO cards
67a67ea29e7 : radeonsi: enable NGG on Navi14 PRO cards
bc3c74e2a29 : radeonsi: tweak LATE_ALLOC_GS numbers for faster NGG culling
b38b5aabee4 : radeonsi: pack LDS better for NGG culling
80943679889 : radeonsi: write VS/TES system values into LDS after culling
1de0bf0a56d : radeonsi: remove indirection when loading position at the end for NGG culling
823ee12d57e : radeonsi: optimize out LDS bank conflicts in the NGG culling shader
7648060dc03 : radeonsi: enable NGG culling by default on gfx10.3 dGPUs
e7d3f22c6ae : radeonsi: don't disable NGG culling on gfx10.3
6810e6e4d0e : Revert "radeonsi/gfx10: disable vertex grouping"
7d1fb5fffe3 : v3dv: Initialize time before usage by free_stale_bos.
8eb246d7f61 : v3dv: Remove unsigned comparison to zero.
5e27e043227 : intel/isl: Drop redundant unpack of unorm channels
cf11ebfbc22 : st/mesa: Add missing sentinels in format_map[]
0c70268ff73 : zink: mark ARB_sample_shading as supported
bf9a1e0a4be : zink: add a pipe_context::get_sample_position hook
b009bd96859 : zink: add ntv handling for ARB_sample_shading
441b32bf3f4 : zink: add helper for vec-type input variables in ntv
7c5129985bc : zink: implement ARB_draw_indirect
3e3b6e995fa : zink: set 3.3 complete in features.txt
80c66642cc8 : zink: bump GLSL to 3.30
44baddf1fe9 : zink: set 3.2 complete in features.txt
26b076ff66f : zink: GLSL 1.50
b27ec49e022 : zink: mark off GL 3.1 as done in features.txt
815f0c01b0f : zink: bump to glsl 1.40
8028991f361 : zink: enable gs pipe caps
4c734da7def : zink: add gallium handling for geometry shaders
d59e4b8ce64 : zink: round out handling for streamout buffer stride setting during draw
9915c540b26 : zink: remove ADJACENCY prim types from primconvert path
d656c600a39 : zink: add handling for gs in ntv
9671cd92151 : zink: re-transform gl_Position for gs input
ea2279daf1f : zink: add ntv handling for geometry shader variables
423a342ae74 : zink: handle shader io vars more generically for use with gs
182f7f9ae8e : zink: add some spirv_builder functions we'll be using for geometry shaders
5934fc17084 : r600/sfn: Update state docu
9f5e5fb9122 : r600/sfn: Fix the parameter component type
5f661977f8e : r600/sfn: Use register keep-alive also when scanning the shader
9eda7176e31 : r600/sfn: fix remapping of deleted attributes
f79b7fcf7c7 : r600/sfn: use 32 bit bools
92a4d45bee6 : r600/sfn: use cacheless op for coherent image write
02e39b737a7 : r600/sfn: Handle mem barrier and image barrier by using ACK
f664fc1c7b5 : r600/sfn: use shared pointer to GPR for FS sysvalues
876b975becb : r600/sfn: Rework get_temp_register to return a smart pointer to GPRValue
92bc0661f5c : r600/sfn: fix mega fetch count for SSBO/Image atomics result fetch
d79d20d398a : r600/sfn: Fix keepalive patch
86254134b38 : r600/sfn: Fix ssbo resource offset for buffer loads
ed66eafb6d8 : r600/sfn: Don't reuse registers for workgroup ID and local invocation ID
bafb2bb5516 : glsl: Initialize add_uniform_to_shader member var in constructor.
aea74eac3d7 : zink: fix stencil wrapping
b17e264e660 : glsl: Initialize lower_ubo_reference_visitor members in constructor.
e32eadc586a : v3dv: Fix assert using assign instead of compare.
e7e24d5039c : intel/fs: Handle nir_intrinsic_terminate
886d2d1a9ab : spirv: Handle SpvOpTerminateInvocation
4dfd2923079 : spirv: Update headers and metadata from latest Khronos commit
f6d5dd825f3 : nir: Add nir_intrinsic_terminate and nir_intrinsic_terminate_if
fdb65b8b237 : aco: add missing SCC clobber in get_buffer_size
6be2bbec6da : Revert "iris: Use the data cache for indirect UBO pulls"
a5529eb235b : anv: Go back to using the sampler for UBO pulls
d91cb31a2aa : vc4: Enable nir_lower_io for uniforms
3e877ca27df : vc4: Add missing range_base/range at nir_load_ubos in yuv_blit fs.
4cfdd425b65 : vc4: Add missing load_ubo set_align in yuv_blit fs.
f91b2fe384a : nir/opt_load_store_vectorize: add some tests for discard/demote behaviour
f8e971f5114 : nir/opt_load_store_vectorize: don't vectorize stores across demote
19aaafd4a66 : intel: Remove Gen10-specific device entries
b0e3af4fb82 : intel: Remove Gen10-speicific perf support
fc04733f093 : anv: Don't generate Gen10-specific functions
5490f5cbceb : iris: Don't generate Gen10-specific functions
495dc514ac8 : intel/isl: Don't generate Gen10-specific functions
1f00b0f4efa : intel: Remove Gen10-specific cache config code
9c19a3874d8 : i965: Don't build Gen10-specific files and libraries
3220ff70f38 : i965: Remove Gen10-specific state setup and workarounds
262ca98b3a4 : intel/compiler: Remove Gen10-specific code
e22f106e017 : intel: Disable all support for Gen10
112f23fd332 : i965: Rename gen10_emit_isp_disable to gen7_emit_isp_disable
fe261091238 : i965: Make MOCS index tables static const
02a0819dcca : i965: Silence many unused parameter warnings in genX_state_upload.c
5a5f30bf434 : i965: Silence many unused parameter warnings in genX_blorp_exec.c
b9c326bc4dd : intel: Silence many unused parameter warnings in blorp_genX_exec.h
de77fabe132 : i965: Allow viewport array extensions with allow_higher_compat_version
9223842c6b3 : ci: Unskip fragment_ops tests on Bifrost
cdfb1d925f3 : zink: add last few format maps for ARB_vertex_type_2_10_10_10_rev
8e96b4f430f : zink: add VK_BUFFER_USAGE_INDEX_BUFFER_BIT to vertex buffer creation
c364124440c : zink: handle null attachment for ARB_texture_buffer_object samplers
69dc0f2f749 : zink: assert valid format in zink_create_sampler_view()
00db994d968 : zink: ensure resource tracking for sampler buffers in render batches
63b299d0134 : zink: implement ARB_texture_buffer_object
4c2b02f5994 : zink: increase descriptor pool sizes for other descriptor types we'll be using
4231cc2e99a : glsl: more accurately handle swizzle in 64bit varying split with no left value
d75d12f5073 : aco: don't use v_pack_b32_f16 if 16-bit input denormals are flushed
d4b3e869ee1 : aco: propagate literals into sub-dword pseudo instructions on GFX9+
1a652244e4b : aco: implement 16-bit literals
91d9c55f3a4 : panfrost: Add blend shader support to bifrost
f04e5ef7ff1 : panfrost: Add missing tile-buffer formats to the format enum
685d45ff938 : pan/bi: Special-case load_input for blend shaders
0d40460757b : pan/bi: Reserve r0-r3 in blend shaders
3432d0a3e53 : pan/bi: Special-case BLEND instruction emission for blend shaders
2f3f5da91de : pan/bi: Collect return addresses of blend calls
8da0a1d5fd4 : pan/bi: Add load_output support
c7748968ba0 : panfrost: Flag blend shader function as an entry point
6d3fce56801 : panfrost: Scalarize nir_load_blend_const_color_rgba
8d707cd9183 : panfrost: Add a "Bifrost Internal Blend" descriptor
e6186c20426 : pan/bi: Support indirect jumps
1a1d9cce465 : pan/bi: Add support for load_blend_const_color_{r,g,b,a}_float
16179c89d11 : pan/bi: Rework blend descriptor access handling
6dd2a76126f : pan/bi: Get rid of the regs argument in bi_assign_fau_idx()
f25850bf5f9 : pan/bi: Use canonical name for FAU RAM sources
111cf7f0e82 : pan/bi: Copy blend shader info from compile_inputs
6c61f0b8e5d : panfrost: Extend compile_inputs to pass a blend descriptor
d8326ceafbd : panfrost: Fix fixed-function blend on bifrost
442f48f27b6 : v3d/compiler: implement load interpolated input intrinsics
3ec165bce99 : broadcom/compiler: track partially interpolated fragment inputs
71ed8c5aa69 : iris: Fix doubling of shared local memory (SLM) sizes.
341f5bffb78 : intel/compiler, anv: Delete cs_prog_data->slm_size
e881290979d : broadcom/compiler: use nir io semantics
9b01598fe5a : nir/lower_io_to_scalar: update io semantics on per-component inst
ac5f0ee19ce : broadcom/compiler: support varyings with struct types
ebd5b555c15 : docs/release-calendar: plan 20.3 release
f8117f70519 : intel/fs: Allow constant-propagation into SAMPLEINFO and IMAGE_SIZE
438a409290a : docs: update calendar and link releases notes for 20.1.10
713b666f290 : docs: add release notes for 20.1.10
0d9216a7cbd : isl: Allow CCS for 8bpp surfaces with 3+ miplevels
f94ba6b6f56 : iris: Add fast-clear restriction for 8bpp surfaces
1affcea37a6 : docs: update calendar and link releases notes for 20.2.1
dee2fdb3da9 : docs: add SHA256 sums for 20.2.1
3c89e7b4229 : docs: add release notes for 20.2.1
bb00a6860ee : radv: fix optimizing needed states if some are marked as dynamic
68daac28df1 : docs: Document how to replicate a CI build locally.
0767af3ffec : ci/android: Switch to using the Android NDK.
ad6189920be : symbols-check: Add __cxa_guard_* to the list of approved symbols.
4722491124e : glsl/tests: Make the tests skip on Android binary execution failures.
f51ce21e4e0 : meson: Drop adding -Wl,--gc-sections to project c/cpp arguments.
d5a72319d6b : aco/isel: Remove now unused VS-related code from create_null_export
c22c702f352 : aco/isel: Remove some dead code
bf51b11c04f : aco/isel: Always export position data from VS/NGG
f29c81f863c : aco: use VOP2 for v_cvt_pkrtz_f16_f32 if possible
7240edec2a6 : aco: use VOP2 version of v_cvt_pkrtz_f16_f32 on GFX_6_7_10
2f125908b35 : radv,aco: lower_pack_half_2x16
dae1e6f7568 : aco: use v_cvt_pkrtz_f16_f32 for pack_half_2x16
9185b7c0698 : aco: add validation rules for p_split_vector
aec872cda0b : aco: use p_split_vector for nir_op_unpack_half_*
f503699e106 : nir/opt_algebraic: optimize unpack_half_2x16_split_x(ushr, a, 16)
a38a497b86c : aco: use p_create_vector for nir_op_pack_half_2x16
3c2abd7116b : aco: expand create_vector more carefully w.r.t. subdword operands
d887eb141bd : aco: propagate SGPRs into VOP1 instructions early.
3424e17b9a9 : zink: unify code for emitting named uint-based variable instructions
20d73a9049f : aco: adjust an assertion about the wavesize in emit_gfx10_wave64_bpermute()
112e66fa090 : aco: compute the CS workgroup size from the shader NIR info
e3e8d13ada6 : radv: move compiler statistics to ACO
97afb2a0a93 : aco: remove unused radv_shader.h includes
408195ec530 : aco: remove useless occurences of radv_nir_compiler_options
8a6f60fc6b8 : aco: remove stub lower_wqm() prototype
23e731fcdba : zink: export PIPE_CAP_MAX*_VARYINGS values
d50e8554b99 : zink: add feature-documentation
f85488ab827 : zink: redo slot mapping again for the last time really I mean it
4f144dc92ce : zink: don't leak sampler view textures
270969b55ef : zink: explicitly flag fb attachments as being written to in render passes
8dfb941a4c5 : zink: add more explicit fencing for transfer maps
e3ed624072e : zink: optimize transfer_map for resources with pending reads/writes
c6687eef2dc : zink: add a mechanism to track current resource usage in batches
48b988e35fe : radv: fix ignoring the vertex attribute stride if set as dynamic
28d02b9d3e7 : ac,amd/llvm,radv: Initialize structs with {0}
b84d1a0c42c : radv/aco: disable NGG GS support because it randomly hangs the GPU
21422b1ff20 : nir/opt_uniform_atomics: remove useless returns
77586647880 : radv: Only close local_fd when valid
4ca6faa933a : util: Hide timespec_passed on Windows
1026e2ac0f7 : radv: Increased const usage
1b551857f98 : amd/addrlib: Fix warning list for msvc
5abac85177d : intel/fs: Rework scratch handling on Gen9+
e557af97811 : intel/fs/ra: Use a set to track added spill/fill instructions
f650c4c0c6b : intel/fs/ra: Sanity-check our IP counts
d80d0a6ced9 : intel/fs/ra: Store the last non-spill VGRF node
2af6528c334 : intel/fs/ra: Refactor handling of Gen7 scratch reads
74a1843ca0f : intel/fs/ra: Increment spill_offset as part of the emit_spill loop
06ebf23283e : intel/fs: Add a SCRATCH_HEADER opcode
24b64c8408b : intel/fs: Copy the PTSS from g0 for scratch reads/writes
f103012fad7 : intel/batch_decoder: Don't clame vec4 vs/gs/tcs shaders on Gen11+
e1efc534e6c : v3dv/device: Support loader interface version 3.
866f9493f4f : v3dv: fix buffer copies to compressed images on the blit path
82b9789f173 : v3dv: drop a couple of obsolete comments
ec78ee0342e : v3dv: limit blit framebuffer dimensions to max coordinates
43063d8de8f : v3dv: generate proper UUIDs for device and driver
c7814bcde3e : v3dv: fix blit path for copies from 3D compressed images
24e46f70b9a : v3dv: fixes for barriers in secondary command buffers
376b009104c : v3dv: implement workaround for GFXH-1918
1e81bb05aeb : v3dv: implement workaround for GFXH-1461
6fb45a04ab3 : v3dv: flag tmu_dirty_rcl in primaries when linking secondaries that have it set
30534fcb29c : v3dv: only advertise one memory type
49549f43c7c : v3dv: always program a reasonable internal depth type for copies/clears
1ed8252514e : v3dv/pipeline_cache: extend pipeline cache envvar
93e3b001c65 : v3dv/pipeline_cache: set a max size for the pipeline cache
7eb8eb10f6b : v3d/compiler: allow to batch spills
f7af9eb2118 : v3dv: free noop job if needed when finishing the queue
cec3d5e7660 : v3dv: clean-up after obtaining an XCB connection
deb0dce1ee9 : v3dv: don't leak dumb BO handles allocated for swapchain images
e7ea9180256 : v3dv/meta_copy: fix TFU blitting when using 3D images
db737a082a8 : v3dv: honor VkPipelineDepthStencilStateCreateInfo::depthWriteEnable
966b14adf71 : v3dv: fix sampling from stencil aspect of a combined depth/stencil image
abca6c97a0d : v3dv/formats: properly return unsupported for 1D compressed textures
0df0449b65c : v3dv: signal semaphore/fence if needed after acquiring a swapchain image
e14cdd6eba1 : v3dv: do not expose VK_IMAGE_USAGE_SAMPLED_BIT for swapchains
e6fb805f9a1 : v3dv: fix size computed by vkGetImageSubresourceLayout for 3D images
83336adacad : v3dv: fix offset computed by vkGetImageSubresourceLayout for array images
4cc7d6a85f2 : v3dv: expose DRM modifiers based on supported features
fdcc36aad40 : v3dv: handle VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_IMAGE_DRM_FORMAT_MODIFIER_INFO
287af8045fb : v3dv/meta_copy: handle mirroring z component bliting 3D images
9518b677f12 : v3dv: fix color clear pipeline destruction for 32-bit architectures
4acf5985a4c : v3dv: hook up robust buffer access
23c727dd673 : v3d/compiler: add a lowering pass for robust buffer access
4401dde0e91 : broadcom/compiler: rename QUNIFORM_GET_BUFFER_SIZE to QUNIFORM_GET_SSBO_SIZE
6f55abcb8b6 : v3dv: handle QUNIFORM_GET_UBO_SIZE
d93d903a377 : v3d/compiler: implement nir_intrinsic_get_ubo_size
f4c754bcd13 : nir: add a nir_get_ubo_size intrinsic
4823313587e : v3dV: move meta init/finish to meta implementation files
db0bb36ace1 : v3dv: don't cache subpass color clear pipelines
07828c0456f : v3dv: fix 3D image blits
0d046516f32 : v3dv: only require texel-size alignment for linear images
57a337f26e0 : v3dv: lower interpolateAt functions in NIR and enable sample rate shading
6004ad9df1d : nir/lower_io: add an option to lower interpolateAt functions
4394efd21ba : v3dv/device: enable largePoints
a0153c92102 : v3dv/device: fix point-related VkPhysicalDeviceLimits
ff02458aa8b : v3d/limits: add line width and point size limits
7620a1b13f3 : v3dv/cmd_buffer: set instance id to 0 at start of tile
fa7fbdb0883 : v3dv/pipeline: set 16bit return_size for shadows always
229cce40562 : v3dv/pipeline: track if texture is shadow
c1bd8e0a1cf : v3dv: Call nir_lower_io for push constants
8f0696781ff : v3dv/pipeline: use derefs for ubo/ssbo
17c5a09c857 : v3dv/device: fix compute_heap_size for the simulator
73b47204aa0 : v3d/simulator: add v3d_simulator_get_mem_size
02b96706119 : broadcom/compiler: allow GLSL_SAMPLER_DIM_BUF on txs emission
e8ceb8f56aa : v3dv/meta: fix hash table insertion
5a59a331e21 : v3dv/pipeline: fix combined_index_map insertions
edec743e8d3 : v3dv/debug: add v3dv_print_v3d_key
ee605bdf3e4 : v3dv/device: warn when the pipeline cache is disabled
54efbe0a036 : v3dv/device: add assert for texture-related limits
29ef4ddcf9b : v3dv: handle multisample rasterization with empty framebuffers
644a15e69e6 : v3dv: implement nir_texop_texture_samples
6ee88f0acde : v3dv: enable sample rate shading if fragment shader reads gl_SampleID
1c4c7d95f71 : broadcom/compiler: track if the fragment shader forces per-sample MSAA
5de282b50a9 : v3dv/descriptor: remove v3dv_descriptor_map_get_image_view
888cefc7976 : v3dv/uniforms: handle texture size for texel buffers
531ea3596da : broadcom/compiler: implement nir_intrinsic_load_sample_pos
b7ca46762f2 : v3dv/formats: fix exposing FEATURE_UNIFORM/STORAGE_TEXEL_BUFFER_BIT
c68ed396b2c : v3dv: handle multisample image clears
4a63b1ae87f : v3dv: handle multisample resolves for formats that don't support TLB resolves
049ea811712 : v3dv: handle multisample resolve of integer formats
a4b68453446 : v3dv: fix blitting of signed integer formats
50351df8285 : nir/glsl: add a glsl_ivec4_type() helper
7bbce22d7be : v3dv: amend tile size tables with smallest tile sizes available
f16da2c8201 : v3dv/device: fix minTexelBufferOffsetAlingment
947fa7033dc : v3dv: add v3dv_limits file
81b713e341a : v3dv/descriptor: support for UNIFORM/STORAGE_TEXEL_BUFFER
14d74c07aa1 : broadcom/compiler: handle gl_SampleMask writes in fragment shaders
3310c1542cc : v3dv: handle multisampled image copies with the blit path
f219795a269 : v3dv: add a blit fallback path for vkCmdResolveImage
6c27dbdbc93 : v3dv: setup texture shader state correctly for multisampled images
006178165c7 : v3dv: handle multisampled image copies in the TLB path
8a1f6717e81 : v3dv: implement vkCmdResolveImage for whole images
b48e01e0cd7 : v3dv: implement subpass multisample rendering and resolve
d953eab5af8 : v3dv: process VkPipelineMultisampleStateCreateInfo properly
d87941cb3ab : v3dv: consider MSAA when computing frame tiling
7c9b40effaa : v3dv/pipeline: handle properly OUT_OF_HOST_MEMORY error when allocating p_stage
d64ff265637 : v3dv/pipeline: pre-generate more that one shader variant
a87d2c78062 : v3dv/pipeline: when looking for a variant, check first current variant
62c32d6ca09 : v3dv/pipeline: remove custom variant cache
35381a46963 : v3dv/pipeline_cache: add default pipeline cache
48a64f28c23 : v3dv/pipeline: provide a shader_sha1 to private ShaderModules
cead2a6db6f : v3dv/pipeline_cache: MergePipelineCaches implementation
8e461b8d71a : v3dv/pipeline_cache: support to serialize/deserialize cached NIRs
a00fe4cb0c4 : v3dv/pipeline_cache: cache v3dv_shader_variants
63b6b633e99 : v3dv/pipeline: add basic ref counting support for variants
2326d5bc04f : v3dv/pipeline_cache: cache nir shaders
1d2ae8756f8 : v3dv/pipeline_cache: bare basic support for pipeline cache
fd70e8e0b01 : v3dv/device: proper pipeline cache uuid
8f46750f461 : v3dv/device: get proper device ID under simulator
ffaab5593c0 : v3dv/device: add vendorID/deviceID get helpers
a2723154c50 : v3dv: fix dynamic state after meta operation
33a6fdb53d4 : v3dv: enable fillModeNonSolid
558987a4652 : v3dv: enable shaderClipDistance
47e02a2ef11 : v3dv: add a fast path for vkCmdClearAttachments
c5d07802dce : v3dv: only clear depth/stencil attachments if any aspect needs clearing
c4564f62aa8 : v3dv: emit new shader state if viewport is dirty
e7678f7c7f8 : v3dv: only care about barriers between GPU jobs
08193cc56f7 : v3dv: avoid prime blit path when presenting WSI images
97891898c33 : v3dv: only use per-buffer clear bit for cases were we are already storing
add87786381 : v3dv: ignore stencil load operation if attachment format doesn't have stencil
1e1903fc1bc : v3dv: use a binning sync for CL jobs waiting on a semaphore
0db95de577b : v3dv: improve pipeline barrier handling
adbce7723e3 : v3dv: don't support sRGB buffer formats
d08da4a54aa : v3dv: handle VK_FORMAT_B8G8R8A8_UNORM vertex attributes
5a2ef59963e : v3d/compiler: support swapping R/B channels in vertex attributes.
a2538b25202 : v3dv: make sure we emit vertex attributes in location order
aebfdfa04c0 : v3dv/device: handle primary nodes for newer kernels
3bd02a729a6 : v3dv: fix color border clamping with specific formats
f156c5dc4d6 : v3dv: fix regressions for cubemap array load/store
9eb1b578eef : v3dv: use swizzle X001 with D/S formats
336d9e187ce : v3dv/image: fix TEXTURE_SHADER_STATE depth for cube arrays
cb1e492ee0b : v3dv: handle unnormalized coordinates in samplers
0385da9e089 : v3dv: fix blit_shader() to honor the region's aspect mask
bf20a5e7b7d : v3dv: fix srcSubresource description for image to buffer blits
6053e85ee45 : v3dv: fix textureSize() for cube arrays
b6c2fde4b9c : v3dv: fix vkCmdCopyBuffer unaligned TLB access
56fcc085fb0 : v3dv: handle draw after barrier
8116d65fbc2 : v3dv: improve handling of too large image sizes
b546155cc34 : v3dv: add workaround for GFXH-1602
f6e7290cbcd : v3dv: fix GFXH-930 workaround
e01d6af98ea : v3dv/device: expose support for image cube array
10b79bf901c : nir: include texture query lod as one of the ops that requires a sampler
b6ccdd59cde : v3dv/uniforms: support for some QUNIFORM_IMAGE_XXX
42b1cacbc64 : v3dv/pipeline: lower_image_deref
407411036c5 : v3dv/descriptors: support for DESCRIPTOR_TYPE_STORAGE_IMAGE
91907560d51 : v3dv: implement support for shader spilling
182e7c2d96a : v3dv: lower frexp
4b869033138 : v3dv: lower unpack_{u,s}norm_2x16
e59e7069283 : v3dv: don't reset descriptor state after a meta operation
4b9e3bbf489 : v3dv: handle empty set layouts
9833a5ae704 : v3dv: initial support for input attachments
19d3639ee7b : v3dv/pipeline: set load_layer_id to zero
6e0cec5a132 : v3dv/pipeline: iterate used textures using the combined index map
b9dd7e30a69 : v3d/tex: avoid to ask back for a sampler state if not needed
0dbf0408634 : v3dv: pipeline initialization fixes for disabled rasterization
d809d9f3f61 : v3dv: don't free BOs from imported memory objects
ddb352b8f96 : v3dv: assert that our framebuffers are single sampled
95caf46602a : v3dv: return a proper error for too large buffer allocations
b356d3de8cf : v3dv: implement indirect compute dispatch
1d6edcc3e82 : v3dv: always emit index buffer state for new jobs
2f1c15116f6 : v3dv: handle unsized arrays in SSBOs
7e990683fde : v3dv: implement compute dispatch
d0b1bb3032d : v3dv: handle separate binding points for compute and graphics
67d5b0c91f8 : v3dv: support compute pipelines
682cfd84d98 : v3dv/bo: add dump stats info
f78c99f357e : v3dv/bo: add a maximum size for the bo_cache and a envvar to configure it
2adea940f1f : v3dv/bo: adding a BO cache
e1a11b81547 : v3dv: always map full BOs
7fb9afcf541 : v3dv: try to use TFU path when creating tiled images from linear buffers
1f8343b8752 : v3dv: add a CPU path for buffer to image copies
1e579956094 : v3dv: add a TFU path for buffer to image copies
e1c8041cde6 : v3dv: try harder to skip emission of redundant state
420d13b3246 : v3dv: actually enable early Z
ca1e29abc45 : v3dv: fix release build warnings
d7278818e35 : v3dv: fix a few cases where we were ignoring suballocated buffers
9bc46136950 : v3dv: regen BO lists for CLs inside cloned jobs
23617021d6d : v3dv/meta-copy: add uintptr_t casting to avoid warning
efb1880b4a9 : v3dv: fix BCL start offset in presence of chained BOs
204c46aa784 : v3dv: warn users that this is not a conformant driver
b2e563151dd : v3dv: add stubs for missing API implementations
9a894849d54 : v3dv/descriptor: use descriptor pool bo for image/samplers
18553b50f94 : v3dv/descriptor: add general bo on descriptor pool
509c8a60c47 : v3dv: don't leak attachment state
3092ddf4d50 : v3dv: support vkCmdClearAttachments in secondary command buffers
ca4b42a51df : v3dv: implement vkCmdWaitEvents for secondary command buffers
6a34ef65655 : v3dv: add basic support for secondary command buffers
fa03471d45e : v3dv: fix bogus command buffer allocation scopes
ce2a7996b25 : v3dv: handle OOM properly during command buffer recording in more places
814dd98df51 : v3dv: ensure BCL space is available before emitting packets
45af2016f3f : v3dv: check that GPU device matches requirements
ca86c7c65a8 : v3dv: assert command buffers are executable when submitting to a queue
8e4cf16da9f : v3dv: remove some unnecessary / unused functions
e048eba81ac : v3dv: drop the extra BO handling from the command buffer
bbdfc5296bb : v3dv: make TLB clearing paths return true/false
a5cede6111a : v3dv: fix vkResetCommandPool
27d360c7026 : v3dv: don't leak BOs from CLs when using BRANCH
e7232252b7b : v3dv/pipeline: support for specialization constants
03f5fae88fc : v3dv/cmd_buffer: move variant checking to CmdDraw
57a254c48de : v3dv: implement events
10dbb1e07da : v3dv: make the driver more robust against OOM
57d0ff8d481 : v3dv: fix depth/stencil clears on hardware
ce681aac70f : v3dv: fix the command buffer private object framework for 32-bit
19576892492 : v3dv: fix dynamic blend constants
98ade03113c : v3dv: implement wide lines
21936e8493a : v3dv: ignore dynamic updates of depth bounds state
9aaf07e5be8 : v3dv: implement depth bias
88a59437d24 : v3dv: drop blit path for depth/stencil formats
5ba9f81c0f8 : v3dv: do not rewrite blit spec for combined depth/stencil in get_blit_pipeline
b0af413edf3 : v3dv: implement partial image to buffer copies
f1b1d5bb8e7 : v3dv: only require 4-byte alignment for linear images
fe0ccdbc830 : v3dv: fix image addressing calculations to account for suballocation
83eb1f254a8 : v3dv/meta-copy: ensure valid height/width with compressed formats
d3c6bd6e7ad : v3dv: always return true from a fallback path if it can handle the case
21633aa1124 : v3dv: implement partial buffer copies to depth/stencil images
df364f9e107 : v3dv: support blitting both depth and stencil aspects at the same time
0a3c7ac9fad : v3dv: implement partial buffer copies to color images
ee4be1ba209 : v3dv: handle copies from/to compressed formats
abea0ec134e : v3dv: limit software integer RT clamp to rgb10a2
3432e51be73 : v3d: fix Tile Rendering Mode Cfg (Color) packet description
e270d2fb14e : v3dv: implement stencil aspect blits for combined depth/stencil format
eac43d06ba8 : v3dv: implement fallback for partial image copies
1b4a9c7d450 : v3dv: properly return OOM error during pipeline creation
2894d6af9f3 : v3dv: handle texture/sampler shader state bo failure with OOM error
05adac2da8a : v3dv: use the private object framework in the meta clear path
f49d9d7c8b1 : v3dv: fix leaks during recording of meta blits
bfadd70d6c2 : v3dv: add framework for private driver objects
e18865b5dd6 : v3dv: support blits with 1D and 3D images
7fecf7ad9e9 : v3dv: remove incorrect assert
8b791a51333 : v3dv: don't support 1D depth/stencil for transfer sources or sampling
94de6a25fbe : v3dv: don't support blitting of combined depth/stencil formats
c441993c9f4 : v3dv: support depth blits
9e304753b6a : v3dv: handle miplevel correctly for blits
05cf7b05948 : v3dv/blit: fix integer blits from larger to lower bit size
63086287e2d : v3dv: don't leak state BO from samplers
71a75a5e785 : v3dv: don't leak the texture shader state BO from image views
a9ce6adf941 : v3dv: don't leak the compiler from the physical device
55729ea7cab : v3dv: don't leak prog_data from shader variants
8e0a3412861 : v3dv: don't leak default pipeline attributes BO
89e426a4fbc : v3dv: don't leak host memory allocated for shader variants
77bccfd828a : v3dv: don't leak NIR code in pipelines
c414a241d0d : v3dv: move early-Z update to pre-draw
ffacf92485e : v3dv: require optimal tiling for features that reqiure sampling
831aa5d4382 : v3dv: implement shader draw fallback for vkCmdBlitImage
5fc55e3a046 : v3dv: save and restore push constant state during meta operations
441d3911b99 : v3dv: save and restore descriptor state during meta operations if needed
689bac310fd : v3dv: meta operations can happen outside a render pass
bd53ee62476 : v3dv: reset subpass index at render pass end
30f1fc25ce5 : v3dv: implement TFU blits
d1b60d2d0c2 : v3dv: add a bunch of API stubs
71ba6a11098 : v3dv: simplify handling of no-op jobs
7ea4601a28a : v3dv: submit a no-op job if a command buffer doesn't have any jobs.
53657b0cb12 : v3dv: implement occlusion queries
8c093246e4c : v3dv: reset all state to dirty when we start a new job for a command buffer
5c826568ab4 : v3dv/format: expose correctly if a texture format is filterable
781dd7ff31a : v3dv: fix subpass merge tests
b94946c23ba : v3dv/uniforms: fill up texture size-related uniforms
9b98d365228 : v3dv/descriptor: handle not having a sampler when combining texture and sampler id
56b611a9cf2 : v3dv: emit instanced draw calls when requested
f41857eb489 : v3d/compiler: implement nir_intrinsic_load_base_instance
ee917d2b78a : v3dv/descriptor_set: combine texture and sampler indices
9d8b1b01c33 : v3dv/descriptor: move descriptor_map_get_sampler, add and use get_image_view
1b80bac236d : v3dv: handle partial clears of just one aspect of combined DS targets
b31ea83b80f : v3dv: simplify partial clearing code
360adff2154 : v3dv: fix incorrect attachment reference
03a150c8ab5 : v3dv: fix incorrect attachment reference
93fd897c28b : v3dv: compute tile granularity for each subpass
f7059e4603b : v3dv: set render area for partial clears to match clear rect
ad64add4f57 : v3dv: create a v3dv_cmd_buffer_subpass_resume helper
debdea6cb5f : v3dv: push/pop more state during meta operations
dedff7446ab : v3dv/descriptor_set: support for immutable samplers
53de8892f47 : v3dv: assert on subpasses that use input or resolve attachments
79b07b85b62 : v3dv: handle stencil load/store operations
7e96f9b2199 : v3dv: restrict render pass clears to the render area
ad0a68df115 : v3dv: use the TLB to clear attachments even if we have an active scissor
4db55731d48 : v3dv: don't always assert that we have an active job
c9b87e9213d : v3dv: fix v3dv_GetRenderAreaGranularity to account for attachment bpp
22d63264491 : v3dv: check the render area against the clip window
e5642a36a01 : v3dv: store the clip window in the command buffer state
d6d8bfbb4a7 : v3dv: implement proper caching for partial clear pipelines
c09c8c0ef35 : v3dv: implement partial depth/stencil attachment clears
7a39e5e9022 : v3dv: implement partial color attachment clears
152a64185b2 : v3dv: improve asserts for VkPipelineColorBlendStateCreateInfo handling
c6dca4c5290 : v3dv: allow to create shader modules from NIR
f47d0829cbe : v3dv/pipeline: fix adding texture/samplers array elements to texture/sampler map
6e39565e596 : v3dv/cmd_buffer: allow return in the middle of variant update if needed
07addb41835 : v3dv/cmd_buffer: update shader variants at CmdBindDescriptorSets/CmdBindPipeline
f76dad8f899 : v3dv/pipeline: add support for shader variants
b6d4148b92f : v3dv/uniforms: filling up QUNIFORM_TMU_CONFIG_P0/P1
272f0d9cfbd : v3dv/descriptor_set: added support for samplers
34910532fd7 : v3dv/pipeline: sampler lowering
522f7110a14 : v3dv/pipeline: unify local allocator name
477b142480d : v3dv/uniforms: cleaning up, moving udpate ubo/ssbo uniforms to a function
f2d16529d13 : v3dv/cmd_buffer: push constants not using descriptor anymore
ca186f72910 : v3dv: fix a1r5g5b5 format
45e86d8a075 : v3dv: don't emit the subpass RCL for jobs that have emitted their own
32d261fad47 : v3dv: fix job subpass index for vkCmdClearAttachments jobs
010589a699d : v3dv: fix clearing of 3D images
3faa7db0533 : v3dv: fix incorrect image slice selection
7de80fad741 : v3dv: use compatible TLB formats if possible during copies and clears
cfc0e15b9bd : v3dv: make sure we only expose transfer features for formats we can use
19841fd5502 : v3dv: check support for transfer usage flags
9e7403d7912 : v3dv: improve assert handling for fallback paths on meta copy/clear operations
d471c47c79b : v3dv: assert on vkCreateComputePipelines
df2bb5b01bf : v3dv: disable depth/stencil testing if we don't have a depth/stencil attachment
e86f381ea1b : v3dv: drop incorrect assertion on number of clear values at render pass begin
a81e63a302b : v3dv: use perp end caps rasterization mode for lines
69ce1f4fd4b : v3dv: only emit config bits and varyings packets if needed
e9030753350 : v3dv/cmd_bufffer: rename and split emit_graphics_pipeline
6bd4e69e9c6 : v3dv: stencil state fixes
c5784fbef4c : v3dv: drop redundant emission of stencil state
7c1910f4533 : v3dv: rewrite dirty state handling
c525849d95a : v3dv: only emit blend state if the pipeline is dirty
1e54b62a619 : v3dv: implement dynamic state for blend constants
4c15131b1d3 : v3dv: always flush draw calls if we are doing sRGB blending
761b0c02f86 : v3dv: add an 'always flush' mode
ebbd3264728 : v3dv: only expose blending on formats that support it
d73bb591131 : v3dv: implement color blending
4c8531a144c : v3dv: fix depth/stencil clear color
03048b26130 : v3dv: fix copies and clears of 3D images
2721c556986 : v3dv: use vk_error() for all queue/submit errors
2fc31a4d28f : v3dv: return OOM error if we fail to import or export sync objects
8ed2e53e0d1 : v3dv: support submits without a command buffer
d9152cb949c : v3dv: only export the last job sync object once
5cfc3b5cc96 : v3dv: handle the case where we fail to allocate a new job gracefully
e5adc33e802 : v3dv: don't leak job allocations
a1337c027cd : v3dv: work around viewport Z scale hardware bug
db629c0f4b0 : v3dv: fix viewport Z
57f5fa08cbb : v3dv: fix scissor outside viewport
5ba6fd3447b : v3dv: fix image tiling configuration
f986a604519 : v3dv: drop assert for map of a mapped buffer
75b1dea4e29 : v3dv: drop incorrect assertion
3e3b8dbfcc9 : v3dv: don't assume that VkPipelineColorBlendStateCreateInfo is provided
2bec99c8a00 : v3dv: lower {i,u}mulExtended
040a3dd739b : v3dv: lower usubborrow and uaddcarry
236e5a7c359 : v3dv: split fragment shader array outputs
51c53969cda : v3dv/device: tweak ssbo/ubo device limits
521f86272bb : v3dv: fix incorrect sizing of the vertex attribute state array
0e5571c704d : v3dv: call nir_lower_io_arrays_to_elements_no_indirects on vertex shaders
1f41a128e03 : v3d/compiler: implement nir_op_fquantize2f16
cb7f1480207 : v3dv/descriptor: take into account pPushConstantRanges
d734dba8a4f : v3dv: implement interpolation qualifiers
02de1d9ab16 : v3dv: add a no-op fragment shader if we don't have one
1811c034db9 : v3dv/pipeline: clean up io lowering
8da4de7c161 : v3dv/pipeline: revamp nir lowering/optimizations passes
518714ae1db : v3dv: drop incorrect assertion
26bfbf29c29 : v3dv: don't reset loader data on command buffers
9b4a1fb9d74 : v3dv: assign driver locations on fragment shader output variables
fadccc1c59b : v3dv: trivial refactors in a few meta copy helpers
313809487cd : v3dv: more frame tiling refactors
2a3fa914d4a : v3dv: rewrite frame tiling setup
44cda4dbfe5 : v3dv: fix subpass tracking in the command buffer state
4a8fdb8ee30 : v3dv: fix framebuffer format when computing fragment shader key
6a909387c2a : v3dv: take memory format from appropriate miplevel for image load/store
5d1089b88df : v3dv/descriptor: support for dynamic ubo/ssbo
404220cc71b : v3dv: fix supertile coverage when render are size is 0.
44370b44e7a : v3dv: implement vkGetRenderAreaGranularity
1af26065561 : v3dv: fix fill buffer with VK_WHOLE_SIZE
d71a5af723a : v3dv: don't support image formats that we can rendet to or texture from
8e163ab2dc7 : v3dv: fix image clearing with VK_REMAINING_*
1ecd188fef0 : v3dv: don't use TLB path for formats that are not supported for rendering
7f3e79ef9f1 : v3dv: don't swap R/B channels for VK_FORMAT_R5B6G5_UNORM_PACK16
aa9ad02e755 : v3dv: implement vkResetCommandPool
c4f745527ec : v3dv: meet requirements for supported format features and properties
e338503c6b1 : v3dv: declare that we support robust buffer access
5dca6dc751e : v3dv: adjust a few limits to comply with CTS minimum requirements
d6afbcb8004 : v3dv: implement host-side event handling functions
aba2a66fb8a : v3dv: implement vk{Create,Destroy}BufferView
43c1fa492ad : v3dv: destroy wsi device during physical device termination
eac594baa55 : v3dv: implement vkQueueWaitIdle
7c4827c1e20 : v3dv: honor swizzle for non-copy operations of color formats
204d06cc267 : v3dv: add assertions for unimplemented fallback paths
79569fb7969 : v3dv: implement vkResetCommandBuffer
ea09600fe6e : v3dv: initialize in_sync_bcl in our submits
83554840a5a : v3dv: add support for primitive restarts on indexed draw calls
914a23a8a0c : v3dv: implement indirect draws
06fa2928b89 : v3dv: add an assert to catch applications trying to clear invalid aspects
9a2d6cca761 : v3dv: vkCmdCopyBufferToImage for depth/stencil formats
f13dd2e6063 : v3dv: implement vkCmdCopyBufferToImage for color formats
e9085e56ed7 : v3dv/cmd_buffer: support for push constants
c8212731e7d : v3d/compiler: handle GL/Vulkan differences in uniform handling
4e2817fd33d : v3dv: implement vkCmdClearDepthStencilImage
11310ee6219 : v3dv: fix buffer automatic stride for image to buffer copies
8da9da87a64 : v3dv: implement vkCmdClearColorImage
1aa5fc04691 : v3dv: implement vkCmdCopyImage
efbf91cb6c6 : v3dv: fix copy size for image to buffer copies
1ee270f8c44 : v3dv: refactor common code in meta copy operations
d39901f416a : v3dv: add a concept of a fake framebuffer for meta-copy operations
7a2544e2d42 : v3dv: move the framebuffer setup code for buffer copy/fill to a helper
5ed78d91fed : v3dv: implement vkCmdFillBuffer
b3f9a3beafc : v3dv: implement vkCmdUpdateBuffer
2f0fbc747c7 : v3dv: implement vkCmdCopyBuffer
18824bf23b7 : v3dv: don't advertise texel buffer support yet.
c7404f4e2d6 : v3dv: Add more supported formats to our format table
83e83257f80 : v3dv: no need to manually add assembly bo to the job
3dff3f3a452 : v3dv: take the number of layers from the framebuffer
0dc4416827e : v3dv: ignore image view aspects for depth/stencil attachments
50652cb919d : v3dv: fix clockwise primitive setting
1c6938484e9 : v3dv: implement indexed draws
f48788896e0 : v3dv: implement vkCmdClearAttachments
255d4245fde : v3dv: add a helper to get the Z/S buffer from an aspect mask
68692297ba6 : v3dv: add a helper to compute the hardware clear color
aa8a61f0aef : v3dv/pipeline: null check for pCreateInfo->pDepthStencilState
34cf4751020 : v3dv/descriptor_set: support for array of ubo/ssbo
9afd24f89a6 : v3dv: initial descriptor set support
7d6fbea536e : v3dv: debug nir shader also after spirv_to_nir
29a7d99c4aa : v3dv: fix the mess with dynamic state handling
134afdfd32c : v3dv: implement dynamic stencil states
d84458b5ded : v3dv: clamp stencil masks and reference value to supported limits
590f29349f3 : v3dv: implement early Z optimization
72040f9182e : v3dv: fix viewport state from pipeline
8d143a02730 : v3dv: support copying depth/stencil aspects to buffer
79b1b684888 : v3dv: fix indentation
b44d4343caf : v3dv/bo: add a bo name
55acd9f1ea4 : v3dv: implement stencil testing
bb6e9d26dcc : v3dv: support depth testing on combined depth/stencil formats
c608e1350be : v3dv: select correct internal type for depth/stencil formats
0e59771339f : v3dv: select the depth/stencil buffer from the attachment aspect mask
df34b8fac64 : v3dv: compute subpass ranges for attachments at render pass creation time
a7a402c8bd2 : v3dv: don't always skip tile buffer stores
4d0e497a3e6 : v3dv: implement support for depth testing
c005a18a566 : v3dv: don't swap RB channels when copying images to buffers
9a72a79d1c2 : v3dv: rename drm device fields so they are more explict
356cf8261e2 : v3dv: allocate winsys BOs properly
1d92c314f85 : v3dv: implement device detection on actual hardware
1ae844c1c89 : v3dv/pipeline: adding some nir-based linking
dc45d57c386 : v3d/cmd_buffer: emit flat_shade/noperspective/centroid flags
6cac991d3f9 : v3dv: stubs for Create/DestroyPipelineCache
6ab4c51d5c6 : v3dv: hook up WSI support
c75846e674e : v3dv: implement DRM modifier setup for WSI
4825a76a226 : v3dv: implement vkGetImageSubresourceLayout
54374f36dfe : v3dv: fix copy image to buffer
beee18103e5 : v3dv: implement VK_KHR_external_memory{_fd,_dma_buf}
0fd434d977a : v3dv: implement VK_KHR_external_memory_capabilities
931b247a7cf : v3dv/format: add R32G32B32A32_SFLOAT format
0fd72b6ac48 : v3dv: implement VK_KHR_get_physical_device_properties2
ecd0b1f4b1c : v3dv: include Vulkan version 1.1 as unsupported.
5935ef098d9 : v3dv: implement vkGetPhysicalDeviceSparseImageFormatProperties
85f1f0690eb : v3dv: provide default values for input attributes
aad44cc614c : v3dv: vertex input support
8c4fcc2bf72 : v3dv/pipeline: lower fs/vs inputs/outputs
45875065fd9 : v3dv: support queue submissions with multiple command buffers
047ee913e8f : v3dv: implement fences
56b4eac8d66 : v3dv: implement semaphore waits and signals on queue submissions
d24dbd87ad1 : v3dv: implement vk{Create,Destroy}Semaphore
0b08f838174 : v3dv: implement vkDeviceWaitIdle
42791451244 : v3dv: prepack VCM_CACHE_SIZE
5226928557e : v3dv: partial prepack of the gl_shader_state_record
0e49c6237ff : v3dv/cmd_buffer: emit CFG_BITS
b60e5ef50eb : v3dv: handle VK_ATTACHMENT_UNUSED properly in more places
04e1a6f3598 : v3dv/cmd_buffer: rename render pass RCL emission helpers to be more explicit
a904b6f082f : v3dv: create a helper to start a new frame
d902e687320 : v3dv: rewrite the attachment needs clearing condition
8a5135e6b37 : v3dv: fix tile buffer loading
22e431e6262 : v3dv: merge subpasses into the same job when possible
0b5df86c98f : v3dv: only clear attachments on the first subpass that uses them
22714890773 : v3dv: rewrite attachment state tracking
6379a552a72 : v3dv: add a note on interactions between clearing and scissor
9f3fd1a3ca9 : v3dv: fix clipping against render area
2baeb91ed7a : v3dv: do not automatically emit a binner flush when finishing jobs
7019700c5fd : v3dv: implement vkCmdPipelineBarrier
856d1020370 : v3dv: use the correct miplevel slice for the tile load operation
3da6e6a190c : v3dv: implement vkCmdNextSubpass
1c8226c6820 : v3d/compiler: update uses_vid/uses_iid check
be1531a8b76 : v3dv/cmd_buffer: start jobs with CmdBeginRenderPass
5259175fe86 : v3dv: add the concept of a job
aef5a5cbca7 : v3dv: implement vkCmdCopyImageToBuffer
94b4e1869cd : v3dv: rename and make compute_tile_size_for_framebuffer() public
00cefce3cad : v3dv: split framebuffer internal bpp calculations from tiling calculations
2b02117e643 : v3dv: add v3dv_write_uniforms
a3b440cc2a4 : v3dv/cmd_buffer: cache viewport translate/scale
e252e536e41 : v3dv: clif format dumping support
15fb14ca1e0 : v3dv/cmd_buffer: add shader source bos to cmd_buffer
8431196eb02 : v3dv/cmd_buffer: start to emit draw packets
67aa8029a80 : v3dv/cmd_buffer: emit shader_state packets
746cfff3a66 : v3dv: flush at the end of each subpass
e163ea1118a : v3dv: emit tile loads
29b6e29378e : v3dv/cmd_buffer: emit Viewport packets
7bfe1db93c3 : v3dv/cmd_buffer: emit Scissor packets
d479f862842 : v3dv/cmd_buffer: init command buffer dynamic state during pipeline bind
f752cdbab1a : v3dv/pipeline: start to track dynamic state
5285d839745 : v3dv: CmdSetViewport and CmdSetScissor implementation
fca4dcee9f2 : v3dv: initial stub for CmdBindPipeline
60145629a2b : v3dv: initial CreateGraphicsPipeline/DestroyPipeline implementation
6cb24a3b39f : v3dv/format: add v3dv_get_format_swizzle
62ca9974761 : v3d/compiler: num_tex_used on v3d_key
3f00638cff3 : v3dv: setup color clear values at subpass setup time
9e6bf4eebcf : v3dv: be more conservative resetting command buffer state
cdc9660662b : v3dv: implement vkQueueSubmit
570ff24d3fe : v3dv: clear set of BOs in the command buffer on reset
bd3c28bf69e : v3dv: keep track of the numbre of BOs in a command buffer
bb727684e8e : v3dv: create the command buffer BO set before we init CLs
6e4471c14c5 : v3dv: implement vkEndCommandBuffer
e6e80d3f9b2 : v3dv: emit the render command list
61399b21c03 : v3dv: emit scissor to render area and precompute hw color clear values
98697e1fb57 : v3dv: precompute more tiling info at framebuffer creation time
3b8aeb7f506 : v3dv: plug leak when destroying device
e6a7d88b531 : v3dv: make v3dv_layer_offset public
14f72ee4f6b : v3dv: implement vkDestroyImage and vkDestroyImageView
4075f8e2219 : v3dv: revert the decision that the command buffer takes ownership of BOs
ec1d7e453ec : v3dv: add the tile state and alloc BOs to the command buffer BO list
ae235e0f225 : v3dv: store base mip level in the image view
52d9b8c05bc : v3dv: add a few more API stubs
bab28ab1e8b : v3dv: make the command buffer own the command list BOs
0020eb4f900 : v3dv: implement vkCmdBeginRenderPass
51705fc0155 : v3dv: compute tile size for framebuffer
cd24292fcab : v3dv: make v3dv_bo_alloc allocate memory for the bo struct
291cd6e77b0 : v3dv: implement vkGetPhysicalDeviceImageFormatProperties
3cf527ab7a5 : v3dv: start handling command buffer status
9bb6d6f1ba9 : v3dv: implement vkBeginCommandBuffer
9ac32610762 : v3dv: add a concept of a command list
dc005f26771 : v3dv: create a v3dv_bo struct and reference it from v3dv_device_memory
d9a7ba317c2 : v3dv: implement vk{Allocate,Free}CommandBuffers
1d8d8c06b8e : v3dv: implement vkCreateCommandPool
e07b657f014 : v3dv: implement vk{Create,Destroy}Framebuffer
c95904f83ed : v3dv: implement vk{Create,Destroy}RenderPass
cdba5361fe8 : v3dv: implement vkCreateRenderPass
582ebb040c1 : v3dv: implement vkBindBufferMemory
5ee155043d6 : v3dv: implement vkGetBufferMemoryRequirements
b478e8c53c2 : v3dv: implement vk{Create,Destroy}Buffer
dee9976200c : v3dv: implement vkCreateImageView
16ec12b7408 : v3dv: implement vkBindImageMemory
e06831454a0 : v3dv: implement vkUnmapMemory
cff9f08d313 : v3dv: implement vkMapMemory
d1d97ea746e : v3dv: implement vkFreeMemory
85632e4685e : v3dv: implement vkAllocateMemory
33bb3956219 : v3dv: initialize mememory heaps in the physical device
4c80097756e : v3dv: implement vkGetImageMemoryRequirements
dc1fbeb0f4e : v3dv: Create/DestroyShaderModule implementation
a201c450007 : v3dv: stubs for graphics pipeline methods
46fa01f4318 : v3dv/debug: add v3dv_debug
ccdc5a7bd4c : v3dv/debug: plug v3d_debug
0fcce6c319f : v3dv: implement vkCreateImage
d5dd157775c : v3dv: add stub for vkDeviceWaitIdle
7a045cf5b37 : v3dv: implement vkEnumerate{Instance,Device}LayerProperties
871ac1ed335 : v3dv: add some basic support for format properties
63e23a9b2a8 : v3dv: add stubs for the format table and vkGetPhysicalDeviceFormatProperties
9cc736f5aa9 : v3dv: add dummy implementations for the packet definition generator
8d9772f6a7e : v3dv: implement vkGetDeviceQueue
41a5719927c : v3dv: implement vkCreateDevice
1c9f9d8fcb2 : v3dv: implement vkGetPhysicalDeviceQueueFamilyProperties
37472a6aa3c : v3dv: amend vkEnumerateInstanceExtensionProperties to handle layers
c2dd7bf6343 : v3dv: implement vkEnumerateDeviceExtensionProperties
10e8967b9b4 : v3dv: implement vkGetPhysicalDeviceFeatures
e75d462950d : v3dv: implement vkGetPhysicalDeviceMemoryProperties
0f0a0145a92 : v3dv: add a comment to clarify how we should implement uuid / deviceID retrieval
9de4ab17c58 : v3dv: retrieve device name from device info
4e88e2d4a9c : v3dv: add support to use v3d simulator
0e0f18ae5e6 : v3dv: Implement vkGetPhysicalDeviceProperties
fc52dc8d7dc : v3dv: pretend to initialize a physical device
36e07a0ab97 : v3dv: memory management stubs
fd81dc64ff6 : v3dv: implement vkEnumeratePhysicalDevices
dbce41f39ba : v3dv: implement vkDestroyInstance
be1575c625a : v3dv: implement vkCreateInstance
20363b0bb95 : v3dv: add support for valgrind macros
2f383f9747d : v3dv: add support for VK_EXT_debug_report
e4af07be760 : gitlab-ci: add broadcom vulkan driver
e5034f0d0d4 : v3dv: add v3d vulkan driver skeleton
bdb1e5aa0ae : glsl: Initialize ir_to_mesa_visitor members in constructor.
6529cbd0bcd : svga: Remove unused printf argument.
12c20cbac0b : util/xmlconfig: Initialize xmlconfig member options in constructor.
77c1b015086 : zink: do not report SSBOs as halfway supported
044d213086b : scons: fix SPIR-V -> NIR build
c122315702a : aco: fix get_ssbo_size with a vgpr resource
a7114f3f46f : nir/opt_uniform_atomics: don't optimize atomics twice
bc436505225 : nir/opt_uniform_atomics: optimize image atomics
bcf7a70008f : aco: use nir_opt_uniform_atomics
f83bc5beb80 : nir: add pass to optimize uniform atomics
37b6b0967ca : nir: allow divergence information to be updated when inserting instruction
e1120f274fd : nir: move divergence analysis options to nir_shader_compiler_options
bb5c0ba0d2e : aco: implement last_invocation
1a912a550f3 : nir: add last_invocation intrinsic
8850a63161a : radv/aco,nir/lower_subgroups: don't lower elect
36da9c4aa2b : aco: implement elect
bf77f539eea : aco: optimize more uniform reductions/scans
c31ababae30 : nir: update ubo locations in nir_lower_uniforms_to_ubo
47c358233d4 : glsl: fix up location setting for variables pointing to a UBO's base
ef0babab38d : zink: ARB_uniform_buffer_object is now implemented, so add cap and feature doc
1b6a80a467f : zink: support loading any UBO
67e4bcb7139 : zink: support non-const offsets
47bdda0f3fe : zink: use nir_lower_ubo_vec4 to simplify things a bit
b9ca4923d6c : aco: implement missing nir_op_unpack_half_2x16_split_{x,y}_flush_to_zero
1070bba19e2 : android: fix SPIR-V -> NIR build
86ededf2967 : docs: fix 20.2.0 relnotes
e57cd6dc198 : docs: fix release calendar
b04f57cb3da : docs: fix relnotes index
c02e933de4a : radv: add missing u_atomic.h include
1fb3e1fb708 : radv: Fix mipmap extent adjustment on GFX9+.
85dfe6118a2 : zink: enable VK_EXT_shader_stencil_export
25d13b0ad06 : zink: add VK_EXT_pipeline_creation_cache_control
bab0d8630c2 : zink: support VK_EXT_extended_dynamic_state
66fc9f5571c : zink: support VK_EXT_blend_operation_advanced
fa2fd72570c : zink: add VK_EXT_custom_border_color
9c43ccd1c27 : zink: enable VK_KHR_vulkan_memory_model extension
66d7bb0f235 : radv: fix adjusting vertex alpha
207138b927f : docs: Add sh256 sums for 20.2.0
ddad8d9c983 : docs: add release notes for 20.2.0
7d72110a1ce : docs/release-calender: Add 20.2 stable releases
63f61b084a5 : docs: update calendar and link releases notes for 20.2
b32a8f83dce : radv: move lower_io_arrays_to_elements before lower_io_to_scalar_early
b0829c6af70 : radv: replace RADV_ALPHA_ADJUST by AC_FETCH_FORMAT
5000c344cc8 : ac/llvm: move AC_FETCH_FORMAT to non-LLVM code
ab067ad6a6a : radeonsi/gfx10: fix stream index for multi-stream overflow query
cf3b638f47b : radv: remove RDR2 discard workaround
037d9fb278c : spirv: replace discard with demote for incorrect HLSL->SPIR-V translations
18f9fc919e1 : spirv: add and use a generator id enum
875ff8414f6 : radv/winsys: Expand scope of allbos lock.
ea778693bf1 : radv: Fix event write cmdbuffer allocation when tracing.
98f538dfca3 : radv: remove one leftover TODO in the shader info pass
cec12d4f985 : radv/llvm: reduce LDS size for tess by using NIR IO assigned locations
47e26bf334a : radv/llvm: reduce the ESGS itemsize by using NIR IO assigned locations
569b8948356 : radv/llvm: switch to NIR IO assigned locations
6387341ccea : ac/nir: pass the variable location to store_tcs_outputs
8f8ee5b95b6 : ac,radv,radeonsi: stop multiplying driver_location by 4
0a90dab6b49 : radv/llvm: stop assigning driver_location in NIR->LLVM
181d5f59b8d : nir: Allow more deref modes in phis
002a23efb42 : android: util: Move xxd.py to util
7346933fc86 : vc4: enable lower_isign for VC4
b7d16adcbe0 : pan/bi: Range check newc/oldc when rewriting
c9b2dfd5aa6 : pan/bi: Disable mediump output lowering
b11cb416881 : panfrost: Temporarily disable FP16 on Bifrost
0bfc7cbe64c : panfrost: Set "shader modifies coverage?" flag
3f919a7269f : panfrost: Update XML for Bifrost early-z/FPK
8cf798d253c : pan/bi: Implement FETCH
7f5428410f2 : pan/bi: Add bi_emit_lod_cube helper
125d18d915a : pan/bi: Map NIR tex ops to Bifrost ops
f42eb33ad2f : panfrost: Fix faults on block-based formats on Bifrost
53637194b21 : pan/bi: Use new block dimension helper
8bb1d61f276 : panfrost: Add panfrost_block_dim helper
aa6a5d20e6b : pan/bi: Don't terminate helper threads
5fdd0c67f7e : pan/bi: Fix message type printing
3ecffd9e6b6 : panfrost: Set helper_invocation_enable for Bifrost
7fdb090709d : pan/bi: Implement txb
5fa5c01aca6 : panfrost: Add some missing Bifrost texture XML
239e4e87fc8 : panfrost: Fix Bifrost high LOD clamp
3943bcec9c8 : panfrost: Fix Bifrost filter selection
401d594c0af : panfrost: Add missing XML for Bifrost samplers
ea85e3abb99 : pan/bi: Prefer 'texture_index' to 'image_index'
3089501757c : pan/bi: Rewrite to fit dest = src constraint
93840234c59 : pan/bi: Pack TEXC
4836366ede9 : pan/bi: Handle nir_tex_src_lod
f8151312af0 : pan/bi: Add data register passing infrastructure
3bf4e60def9 : pan/bi: Stub out TEXC handling
dcce3feb79e : pan/bi: Add texture operator descriptor
d99df25d5d4 : pan/bi: Pack skip bit for texture operations
39ec3eb6e7d : pan/bi: Encode skip bit into IR
5cf53d121c9 : pan/bi: Streamline TEXC/TEXS naming/selection
6ed1bdfee4b : pan/bi: Use canonical texture op names in IR
93f9052935f : pan/bi: Fix simple txl test
c3796c9f025 : pan/bi: Expose GL 2.1 on Bifrost
a204eac7599 : pan/bi: Handle vector moves
a22779866ac : pan/bi: Pass flow_control through directly
0f181f4eaeb : pan/bi: Use canonical flow control enum
d2328646b22 : pan/bi: Use canonical term dependency
2b9484c2c82 : pan/bi: Use canonical term "message type"
800ee3d3033 : pan/bi: Print message types as strings
77a4e39100a : pan/bi: Add missing message types
d2fac19999b : pan/bi: Expand clause type to 5-bit
785344e6555 : pan/bi: Use canonical name for staging registers
4131bc3b0cb : pan/bi: Use canonical next_clause_prefetch
6c1cabc288e : pan/bi: Canonicalize terminate_discarded_threads
a5975883b94 : pan/bi: Use canonical floating-point modes
c8b9a05f9e7 : pan/bi: Cull unnecessary edges on the CF graph
026a29506e4 : pan/bi: Drop if 0'd combine lowering
405544eae56 : pan/bi: Fix memory corruption in scheduler
7c351a6f5d4 : pan/decode: Ensure mappings are zeroed
3ed7472b2a2 : pan/bi: Add copy for register COMBINEs
556bb178926 : ci: piglit: conditionally build OpenCL tests
d5e5f72e061 : vc4: Enable lower_umax and lower_umin
e7127b3468c : nir/algebraic: optimize iand/ior of (n)eq zero when umax/umin not available
210db65b1a1 : panfrost: Add a debug flag to disable AFBC
205f1d79e24 : radeonsi: disable SDMA on gfx6-7 and gfx10.3 to decrease CPU overhead
7a0162905b1 : radeonsi: update the DMA perf test
4182fbcb609 : winsys/amdgpu: apply the VM alignment optimization to the physical alignment too
99446b8ceef : winsys/amdgpu: rework the VM alignment optimizations
a4e4644eff4 : ac/surface: fix valgrind warnings in DCC retile tile lookups
b0df97b576e : CI: build our own spirv tools
d166188b848 : ci: fix deqp clone + fetch
5de56937a3d : disk_cache: build option for disabled-by-default
8e981453ed6 : radv: use radv_optimize_nir() less in radv_link_shaders()
55254f241fe : radv: move optimizations in shader_compile_to_nir() to after io_to_scalar
5f2671bcc5f : nir: return progress from nir_lower_io_to_scalar_early
fd4d0b447c0 : panfrost: Move the blend shader cache at the context level
a5005c349d0 : panfrost: Get rid of the constant patching done on blend shader binaries
c9739941ba4 : panfrost: Let compile_blend_shader() allocate the blend shader object
dbc33e8854e : panfrost: Don't leak NIR blend shaders
8a5b885c94a : panfrost: Allocate blit_blend with ralloc()
0a74a04ba56 : panfrost: Pass compile arguments through a struct
78ec5225c2a : panfrost: Move the blend constant mask extraction out of make_fixed_blend_mode()
4441e803554 : panfrost: Constify the rt_fmts arg passed to pan_lower_framebuffer()
da132d802b8 : radv: Set fce metadata correctly on DCC initialization.
5ae3656890f : aco/ngg: Calculate workgroup size of NGG shaders.
61280bb4b66 : aco/ngg: Allocate NGG GS space early for const vertex/primitive counts.
e8a0409d01e : aco/ngg: Use more efficient LDS layout to help reduce bank conflicts.
9bf92d43571 : radv/aco: Enable NGG GS by default.
dd73719856c : aco/ngg: Add shader query support to NGG GS.
df62c8fbeac : aco/ngg: Place workgroup barrier outside control flow for NGG GS.
1129575d5ed : aco/ngg: Implement NGG GS output.
62b5012ec35 : aco/ngg: Implement workgroup reduce / exclusive scan for NGG GS.
c29e288fb51 : aco/ngg: Create LDS layout for NGG GS.
2680329fb76 : aco/ngg: Setup NGG GS.
9c3d8404dea : aco/ngg: Allow NGG GS to create VS exports.
b67878f3283 : aco/ngg: Allow NGG GS to load per-vertex GS inputs.
8f25d9f821d : aco/ngg: Allow NGG GS to store ES outputs.
b57b1a06e42 : aco/ngg: Clean up and reorganize NGG VS/TES code.
3645a3106a0 : aco/ngg: Make primitive export packing less prone to error.
0bfe0495c1b : aco/ngg: Refactor ngg_emit_prim_export in preparation for NGG GS.
b08ced08a22 : aco/ngg: Refactor gs_alloc_req in preparation for NGG GS.
ecfabfd6069 : aco: Add wave-specific opcode for s_lshl and s_flbit.
57d8799284f : aco: Optimize thread_id_in_threadgroup when there is just one wave.
5e31fb49a3b : aco: Use thread_id_in_threadgroup helper for ES outputs.
924f816fe17 : aco: Extract thread_id_in_threadgroup to a separate function.
b1964ad4d6c : aco: Extract lanecount_to_mask to a separate function.
0b8e7be0830 : aco: Clarify missing export error message in assembler.
c1d11bb92c9 : aco: Add loop creation helpers.
17ad2ade82f : radv/aco: Use new GS lowering options for ACO with NGG GS.
f11f4a2a4da : nir: Add ability to count primitives per stream.
aac5adc3c2c : nir: Count vertices per stream.
70b94adddb7 : nir: Add ability to overwrite incomplete GS primitives.
c977c369d35 : nir: Add ability to count emitted GS vertices per primitive.
2be99012e95 : nir: Add ability to count emitted GS primitives.
73dd86c4214 : radv,anv: use CLOCK_MONOTONIC_FAST when CLOCK_MONOTONIC_RAW is undefined
fe894dc0b33 : util/os_misc: os_get_available_system_memory() for FreeBSD
9aa5c7ce721 : radv: use the same NIR compiler options for both compiler backends
63049b04446 : radv/llvm: do not lower sub
abce2718d6d : lima/parser: Fix varyings decoding in RSW
6db3df5c2f1 : aco: dump the program if the disassembler failed
a7d3be78ce2 : clover: don't call validate spirv at all if not needed
91ace074d2e : util/disk_cache: remove unused function param
5931d783c8b : swr/rasterizer: Remove BuilderGfxMem member mpTrackMemAccessFuncTy.
4b513136b1b : meson: Use more portable compiler option -std.
3a1f22c38b1 : turnip: Add support for GetSwapchainGrallocUsage2ANDROID().
5a595cd3af1 : turnip: Detect Qualcomm gralloc and its UBWC flag on gralloc surfaces.
9a14e747525 : turnip/kgsl: Add support for importing dma-bufs.
b732e4f2747 : turnip/kgsl: Fix last minute breakage of the build.
290f3fe8972 : Revert "anv: Add driconf option to disable compression for 16bpp format"
cce6fc3b5c7 : anv: Enable multi-layer aux-map init for HIZ+CCS
624a2aad669 : freedreno/ir3: Don't leave holes the UBO upload plan.
ddf468f96f8 : freedreno/ir3: Clean up the UBO upload plan setup.
330c68d3c20 : ci/softpipe: Add another flaky GS test to the skips list.
0b96b7bf10d : util/hash_table: add function for reserving size in a hash table
06a5edf247d : nir/opt_deref: Fix the vector bitcast optimization
54eae335587 : clover: Stop leaking NIR shaders
cc00d57a3c0 : util/xmlconfig: eliminate memory leak
11389849a4e : radv/llvm: remove dead code for 64-bit GS inputs
a41bed243e9 : radv/llvm: do not lower nir_op_fsat
31a0574b968 : ac/nir: implement nir_op_fsat
0747f21bb67 : ci: Disable pm_runtime and max clocks in LAVA jobs
7cae9f0ef13 : ci: Test Panfrost on Khadas VIM3 boards
b74cfa78619 : ci: Update kernel for LAVA
981464356c0 : freedreno/a6xx: Support PIPE_FORMAT_R8_G8B8_420_UNORM for texturing
11563da8fa8 : freedreno/a6xx: Generalize pointers in struct fd6_pipe_sampler_view
826a10255f5 : st/mesa: Add NV12 lowering to PIPE_FORMAT_R8_G8B8_420_UNORM
e23bcb69c35 : util/formats: Add PIPE_FORMAT_R8_G8B8_420_UNORM
3b784370c37 : iris: Use the data cache for indirect UBO pulls
b54d37a8676 : anv: Use the data cache for indirect UBO pulls on Gen8+
89f3d116a8a : anv: Plumb the device into *bits_for_access_flags
3a335606813 : anv: Use format_for_descriptor_type for descriptor buffers
d2185f0c3f0 : anv: Add a device parameter to format_for_descriptor_type
3d22de05ca1 : intel/fs: Add an option to use dataport messages for UBOs
0d462dbee57 : intel/fs: Add an alignment to VARYING_PULL_CONSTANT_LOAD_LOGICAL
459f68af3c9 : i965: Take an isl_format in emit_buffer_surface_state
caea5a6a20f : intel/dev: fix 32bit build issue
dd9c34a907c : intel/nir: Lower load_global_constant in lower_mem_access_bit_sizes
fd04f858b0a : intel/nir: Don't try to emit vector load_scratch instructions
0a172dca264 : ci: enable piglit testing of clover/llvmpipe.
0cb17757ff7 : CI: Don't run pixmark-piano twice on radeonsi
2fa7c790457 : spirv: Move nir_lower_libclc to src/compiler/spirv
43390a546d9 : clover: Use core libclc loader
ef453f54394 : spirv: Add a shared libclc loader
5ffdb1092be : meson: generalize libclc usage
ed7e962b07c : clover/meson: use dep.get_variable instead of deprecated get_pkgconfig_variable
d3dcb1184bf : util/xxd.py: Add an option for binary files
82bbf4c3f23 : util: Make xxd.py output char array instead of string
22ffc05266c : util: Move xxd.py to util
3ff513ee5d9 : glsl/xxd.py: fix imports
449f1fee9e9 : gallium/pipe: Add a GALLIUM_PIPE_SEARCH_DIR override env var
1d3600c156f : iris: Fill out compute caps and enable clover support
9df9f940f01 : iris: Add support for load_work_dim as a system value
67ee9c5f553 : iris: Handle runtime-specified local memory size
d9adb55a4d8 : iris: Add pipe-loader support
8de380d26a0 : broadcom/compiler: add V3D_DEBUG_RA option
bcb8dd74327 : broadcom/common: increase V3D_MAX_TEXTURE_SAMPLERS, add specific OpenGL limit
5f7810dcb2b : aco/isel: Fix out-of-bounds write in visit_load_input
d38094bb33b : radv: Respect alignment requirements in descriptor set layouts
3b55913f330 : radv: Clean up CreateDescriptorSetLayout
76add3565e2 : radv: Fix unaligned memory access when writing specialization map entries
984dcfc59fa : radv: Avoid calling memcpy with null pointers
0ef2f1d4a00 : nir: Fix unaligned pointer access
6a9dc75cc23 : nir: Fix undefined behavior due to signed integer multiplication overflows
137d7d29fa1 : ci: move to using clang 10 for meson + clover
ae7189df6e8 : st/mesa: pass inlinable uniforms to drivers if they requested it
593517a775a : gallium: add pipe_context::set_inlinable_constants
3f1b35a2f03 : nir: add new helper passes that lower uniforms to literals
10a76824137 : util: add _mesa_set_create_u32_keys where keys are not pointers
7f2ea2a433c : panfrost: Fix fixed-function blend on Mali v6
8389976b7c0 : panfrost: XML-ify the blend descriptors
ca392e8cd77 : panfrost: Rework the render target layout to use overlapping structs
713419eef04 : panfrost: Rework fixed-function blending
f2044044e64 : panfrost: gen_pack: Add a no-direct-packing attribute
4205c95b34c : panfrost: gen_pack: Support overlapping structs
3d09e260fbd : panfrost: gen_pack: Drop support for opaque structs
01121c795bd : panfrost: Drop the with_opaque specifier on midgard blend desc
7bb85eadebf : panfrost: Get rid of the with_opaque qualifier on the renderer state desc
f734e67b93d : panfrost: Adjust the renderer state definition
51331d6d576 : panfrost: Adjust the primitive desc definition
d343f233454 : panfrost: Adjust the draw descriptor definition
1e7d82c8813 : nir/algebraic: always lower idiv to shifts if bitops are allowed
315df8dbb8d : glthread: handle glInterleavedArrays
bd70b61f2f6 : mesa: remove api_loopback to remove call indirections
4bd94bd2270 : mesa: don't use GET_DISPATCH because it doesn't work with glthread
fd3209a974f : clover: move tokenize function to algorithm
ee5b46fcfdb : clover/spirv: support CL_KERNEL_COMPILE_WORK_GROUP_SIZE
2bb2ba7e340 : clover/spirv: parse arg_info
4f998266911 : clover: avoid adding an extra space to compiler options
811b17a207b : clover: implements notification callback on program builds
c04d5e7efa7 : clover: implements clGetKernelWorkGroupInfo CL_KERNEL_COMPILE_WORK_GROUP_SIZE
aadd1340814 : clover: add CL_KERNEL_ATTRIBUTES for clGetKernelInfo
ef0f8ec03bf : clover: bind sampler_t type to module::argument::sampler
9aea6e33740 : clover: implements clGetKernelArgInfo
d7d66e30f22 : clover: implements clEnqueueFillImage
c0f03f6fc03 : clover: implements clEnqueueMigrateMemObjects
4b96eb0cc47 : etnaviv: Make sure to track different pipe_screens for different DRM device descriptions
ac161102f35 : panfrost: Fix a warning
ccb3d7d8bea : panfrost: bifrost: disassemble: Fix decoding of next_regs
19561f31a87 : radv: remove trailing whitespace
8096e0df7a9 : aco: remove trailing whitespace
3c5eb1f7615 : aco: more uses of nir_get_io_offset_src()
1211d05befa : aco: bail out if the NIR IO base offset isn't zero
9d5ec7f6f2c : etnaviv: stop leaking the dummy texure descriptor BO
6a44bda8795 : intel/uuid: use git-sha1/package for the driver UUID
456fa9b8385 : iris: plumb device/driver UUID generators
e9a766a8c02 : intel: split driver/device UUID generators
713386af203 : turnip: Enable support for KHR_incremental_present
8b205402c34 : omx/tizonia: fix build
f5f0c012ad3 : gallium/util: remove empty file u_half.h
71697953ec5 : gallium/util: remove redundant util_float_to_half_rtz
b42c6ff6f61 : util: remove util_float_to_half and util_half_to_float wrappers
24a62dd0fb0 : util: move util_half_to_float code into _mesa_half_to_float_slow
ffcdf76799b : util: implement F16C using inline assembly on x86_64
4c54f059150 : nir/constant_folding: init nir_const_value to zero
335132cd4dd : lavapipe: drop dri,dricommon deps.
9c256892873 : intel: drop likely/unlikely around INTEL_DEBUG
e06da554e9e : anv: drop likely/unlikely around INTEL_DEBUG
4b9e38ca068 : i965: drop likely/unlikely around INTEL_DEBUG
e6d26fbf3db : iris: drop likely/unlikely around INTEL_DEBUG
4015e1876a7 : intel: add INTEL_DEBUG expected value in declaration
bcfec61d1ee : anv: Add driconf option to disable compression for 16bpp format
49593205b98 : anv: Factor out dri option initialization code in separate function
7c6f1d3bf99 : clover/nir: extract constant buffer into its own section
adbfff6eae8 : clover: bind constant buffer if one is provided
af85985250a : clover/util: add id_type_equals to support symbols with multiple sections
7fb4ab9ec12 : driconf: Restore the ability to override driconf with the environment.
455bfecdffc : driconf: Make sure that the range check on the defaults actually works.
24b4a63b3d0 : CI: Re-enable Panfrost T7xx CI
3dc00c33f08 : gallium/u_threaded_context: fix use-after-free in transfer_unmap
706fef711ba : gallium/u_threaded_context: always flush asynchronously if requested
28256d3d7b4 : gallium/u_threaded_context: don't call memcpy in tc_set_constant_buffer
ed3c5fe4694 : radeonsi: implement GL_INTEL_blackhole_render
bad7b38aa19 : radeonsi: remove dead variable postponed_kill
d5575ca7a14 : gallium/util: add set_frontend_noop into driver_noop and u_threaded_context
72fa3372cc0 : util/idalloc: resize if ID is too large for reservation
155b1b17921 : st/mesa: enable GL name reuse for queries based on the driconf option
6f7446bda56 : driconf: enable force_glsl_extensions_warn for viewperf
a8b4e690cfc : driconf: force the vendor string to NVIDIA to fix viewperf energy tests
5827fe898e9 : gl_marshal.py: inline print_sync_dispatch
bcd6b0c6855 : mesa: factor out layout parsing for glInterleavedArrays
60825a542de : nir/constant_folding: Fold load_deref of nir_var_mem_constant
481b7538abf : nir: Validate constant initializers
1ada83504fe : nir/constant_folding: Use nir_shader_instruction_pass
9df1ff36781 : nir/constant_folding: Use the builder
3b11b37a1be : radv: remove VkPipelineCacheCreateInfo::flags assert
3f3a5f3489f : iris: Fix a fast-clear skipping optimization
c416adfb2d9 : anv: remove VkPipelineCacheCreateInfo::flags assert
9ad4b8b9243 : intel/dev: add a small non installable tool to print device info
61c095f09a7 : zink: enable pipe caps for ARB_timer_query
bb603352b68 : zink: add pipe_context::get_timestamp hook
b551ee22dfc : zink: handle TIME_ELAPSED queries
7a40b734ee2 : zink: handle timestamp queries
79f35444126 : intel/perf: fix crash when no perf queries are supported
82563b6a9fa : util: drop non-posix header fnmatch
f0707e977b8 : CI: Disable Panfrost T7xx CI
2b977adff80 : xmlconfig: fix scandir_filter
a0c13c9de9a : spirv: Make the clc_shader const
e33f9dbc1af : turnip/kgsl: Add strerror decode in BO init failure.
5d3aeafa772 : turnip: Report device loss through _mesa_loge() instead of fprintf.
50f25da2b54 : turnip: Always enable TU_DEBUG=startup on debug drivers.
a4d9a9d11c3 : turnip: Extend the coverage of TU_DEBUG=startup.
80869f0bc3a : turnip: Mark the vk_errorf helper as bring printflike.
01de452b5d5 : turnip: Use mesa's normal PRINTFLIKE macro instead of our own.
a7bc2f8d1b5 : turnip: Don't expose VK_ANDROID_native_buffer on non-Android.
d82826ad444 : anv: Implement VK_EXT_transform_feedback on Gen7
9831888b682 : android: panfrost: use python3 for generated sources rules
27921171e34 : android: pan/bi: Use new disassembler (v2)
8163c818e32 : turnip: implement timestamp fences/semaphores for kgsl backend
462d62351d2 : broadcom/simulator: update to a newer simulator
e3b814d5e9e : zink: hook up driconf
f984654da8b : ac/nir,radv: fix invalid IR when loading inline uniform blocks
9badadf67eb : radv: remove dead deref code in the shader info pass
bc099b834fd : radv: remove unused gs.writes_memory in the shader info pass
9896337d1b2 : ac,radv,radeonsi: remove unused parameters in the shader ABI IO
b7f99401f4b : radeonsi: remove dead code in TCS/TES/GS since const_index is always 0
e3296e05ae3 : ac/nir: remove dead shader IO code
456f63e0ba1 : ac/nir: remove dead global load/store/atomic derefs code
6b0695c42a2 : radv/llvm: enable lower_unpack_half_2x16
f11d4f31270 : ac/llvm: implement nir_op_unpack_half_2x16_split_{x,y}
cdf6d934987 : radv/llvm: lower VS IO
b3402997a52 : radv/llvm: gather VS input usage mask from load_input
1c4a21328e1 : radv/llvm: lower TCS IO
80cefee0f72 : radv/llvm: gather TCS outputs from the output variables
96152739072 : radv/llvm: lower TES IO
6e339418a72 : radv/llvm: lower GS IO
ed55bc4af2b : radv/llvm: assign driver locations for VS, TCS, TES and GS correctly
1ea48c1f57d : ac/nir: remove dead load/store deref code for temporary variables
7a8f5eab71a : ac/llvm: adjust dmask when image stores are shrinked using the format
961a8d71cdc : vc4: Avoid negative scissor caused by no intersection
9a899e579a6 : v3d: Update the TEXTURE_SHADER_STATE when there’s a new buf for a tex
e2f037e96cb : v3d: Split the creating of TEXTURE_SHADER_STATE into a helper function
d25504dae01 : v3d: Make the function to set tex dirty state for a stage global
ef918f0e335 : turnip: remove pre-emption marker
3b3a3af9c76 : glsl: Initialize ast_node member field location.path in constructor.
81cd4c8f596 : intel/vec4: Remove leftover code from Gen8+ removal.
0a7bd14dbb8 : freedreno: Move rsc NULL check to before rsc dereferences.
1b0fec444fd : iris: Fix the constant data address calculation
23ff2a0e634 : nv50/ir: Initialize Source members.
7e862670efb : radv: Fix asserts using assign instead of compare.
9660427ab7b : lima: Print usage if --help is any of the arguments.
2fb27499378 : android: Disable the user XML config parsing.
7edb2aed551 : util/xmlconfig: Drop use of XML_Char in parsing.
6f3352b6a76 : driconf: Stop quoting true/false in boolean option definitions.
8a05d6ffc65 : driconf: Make the driver's declarations be structs instead of XML.
9fbf206a137 : driconf: Use DRI_CONF_OPT_I for remaining int options
23c3eb1fe16 : driconf: Delete disjoint range support.
4f37161a8f2 : util/xmlconfig: Indent to Mesa style.
91ccbb399f0 : util/xmlconfig: Drop silly open-coded strdup.
df3d3ea33e7 : driconf: Make a DRI_CONF_OPT_S() for string options.
4a573849593 : r200: Reuse DRI_CONF_OPT_F for texture_blend_quality.
c47c08fa72b : driconf: Fix extra quoting on "Jimenez'".
b1e730b3b43 : driconf: Eliminate the DRI_CONF_OPT_BEGIN_B macro.
8427e560672 : intel/fs: Don't use NoDDClk/NoDDClr for split SHUFFLEs
b23541c4d3a : android: util: add log.c to Makefile.sources
f9977f87296 : panfrost: decode: Flag pandecode_log_typed() as PRINTFLIKE
12b00b77c6f : panfrost: decode: Fix decode_bifrost_constant() prototype
7568c97df14 : radv: Use atomics to read query results.
7cc55df938b : pan/bi: Fix assert when writing vertex outputs
447cef4a71d : zink: use sizeof(vec4) multiplier for nir_lower_uniforms_to_ubo
1c8e80a07b8 : zink: correctly set up ubo bindings and buffer indices
59027a26828 : zink: don't emit ubos or bindings for ubo variables
d369c00c83c : zink: emit ubo variables sized based on the overall ubo block size
76ac3416755 : zink: always emit descriptor set 0 in ntv
9a8539206f9 : zink: fix shader buffer size caps to use 65536
0e3e3232246 : zink: run nir_lower_uniforms_to_ubo conditionally
7767c3dae30 : zink: correctly handle ARB_arrays_of_arrays in ntv for samplers
18fd6274b26 : aco/tests: add disassembler tests to reproduce the add3+clamp crash
01704dd1a41 : aco: apply the clamped integer addition disassembly workaround for v_add3
c9192d1083e : pan/mdg: map uabs_i/usub to i/uabsdiff
cea032a3459 : pan/mdg: remove unused arg from ALU_CHECK_CMP and ALU_CASE_CMP
37c1b9c54b7 : aco: fix get_buffer_resource_flags()
b2e1fc8976d : nir: Add a pass to lower vec3s to vec4s
9190f82d573 : nir/opt_deref: Add an optimization for bitcasts
80e6ac3341c : nir/opt_deref: Add an instruction type switch
769ede2de49 : nir: Add component mask re-interpret helpers
57e7c5f05eb : nir/opt_load_store_vectorize: Use bit sizes when checking mask compatibility
f6667cb0ce8 : nir: Add a memcpy optimization pass
e363da3bdd3 : nir: Handle memcpy in copy_prop_vars and combine_stores
100a5ace636 : nir/find_array_copies: Properly discard copies for casts
1c492995357 : gallium/util: allow scissored blits for stencil-fallback
e7e0468f730 : gallium/util: fix memory-leak
03bea54e029 : meson: fix power8 option
57b4f60add3 : turnip: don't initialize GRAS_LRZ_CNTL/RB_LRZ_CNTL tu6_init_hw()
3c07a149986 : turnip: enable LRZ
1d83f5ae843 : turnip: disable LRZ on vkCmdClearattachments() 3D fallback path
2f79e006640 : turnip: disable LRZ on vkCmdClearAttachments()
27743b029d4 : turnip: emit correct LRZ fast clear setup
0ca87ed5062 : turnip: add support to clear LRZ
0b2cfd0668e : turnip: add LRZ valid tracking for secondary command buffers
517b26bdd10 : turnip: add LRZ tracking to command buffer state
fdad1ca2565 : turnip: disable LRZ depending on fragment changes
d1fa40bdcfc : turnip: disable LRZ writes when blend is enabled
38f008e07bc : turnip: disable LRZ on specific cases
6089b00e893 : turnip: create LRZ buffer
138d2928cd9 : turnip: add environment variable to disable LRZ
e3c7748b2e2 : ci/bare-metal: Move the "POWER_GOOD not seen in time" check to the right time.
98bb74b67df : nir: Fix a misspelling
038fcbcaed3 : glsl: don't duplicate state vars as uniforms in the NIR linker
535fd6d45e6 : freedreno/cffdec: fix decoding of bindless descriptors
a8ac61b0ee2 : intel/fs: NoMask initialize the address register for shuffles
5c2129d4347 : virgl: fix stride + layer_stride inconsistency
87383e3163d : virgl: query blob mem
3b54e5837a1 : virgl: support PIPE_CAP_BUFFER_MAP_PERSISTENT_COHERENT
cd31f46f08a : virgl/drm: add resource create blob function
e01ec6ed2d4 : virgl/drm: query for resource blob and host visible memory region
7b7f2108256 : drm-uapi: virtgpu_drm.h: resource create blob + host visible memory region
c73c0cc3177 : virgl: add flags to (*resource_create) callback
1aac47db69d : Revert F16C series (MR 6774)
4a0164ed85f : android: gallium/virgl: cleanup virgl_driinfo.h gen rules
d7fbf94ae84 : android: gallium/radeonsi: cleanup si_driinfo.h gen rules
a648aea3fdf : android: gallium/iris: cleanup iris_driinfo.h gen rules
cb95065dd12 : nir: Add lowering from regular ALU conversions to the intrinsic
bc7ed03ef8f : clover/nir: Call nir_lower_convert_alu_types
7d97f3dfdc8 : spirv: Implement vload[a]_half[n] and vstore[a]_half[n][_r]
a85afb797e7 : spirv/opencl: Drop dest_type from handle_v_load_store
8610af12b6a : spirv: Handle all OpenCL conversion ops with full rounding
8e8458218c6 : spirv: Add some conversion handling helpers
383ecfbc709 : nir: Add a passes for nir_intrinsic_convert_alu_types
d5cb51e2b91 : nir: Add builder helpers for OpenCL type conversions
588bb6686b3 : nir: Add a conversion and rounding intrinsic
0aa08ae2f67 : nir: Split NIR_INTRINSIC_TYPE into separate src/dest indices
4c70f1ba2fb : gallivm/nir: fix non-32 bit find lsb/msb
e8f1cc41db3 : llvmpipe/cs: add in shader shared size.
35b162eb2c0 : gallivm/nir: make sure to mask global reads.
545d852a7a7 : intel/gen9: Enable MSC RAW Hazard Avoidance
237f4d9d187 : radeonsi: restructure si_pipe_set_constant_buffer
d5cb7bd5274 : radeonsi: call nir_lower_bool_to_int32 last because it breaks nir_opt_if
fd6bbdcf59d : radeonsi: use staging buffer uploads for most VRAM buffers
701f7ae9d25 : radeonsi: move si_set_active_descriptors_for_shader into si_update_common_shader_state
f5912c6d326 : radeonsi: kill disabled clip distances and planes at per-channel granularity
30c3b2c0b60 : radeonsi: simplify NGG culling enablement and add radeonsi_shader_culling option
b02bef01c89 : intel/blorp: Conditionally clear full surface depth and stencil
d5849bc840e : anv: Skip HiZ and CCS ambiguates which preceed fast-clears
e9d5ec342d1 : anv: Use more temp vars in cmd_buffer_begin_subpass
7c92e413afe : anv: Allow HiZ clears for multi-view
03af98abe26 : radeonsi: support for external buffers (ext_external_objects)
df634915944 : radv/aco: lower IO for all stages outside of ACO
2c322514f38 : radv: gather output usage mask from store_output for VS, TES and GS
79368ab302f : ttn: Fix number of components for IF/UIF
b00a023f1e1 : ac/nir: fix nir_intrinsic_shared_atomic_fadd
8227b08c081 : ac/llvm: fix invalid use of unreachable in ac_build_atomic_rmw()
892e74d2f7c : radv: fix gathering writes_memory for global store/atomic operations
e94fd4cc658 : lavapipe: rename vallium to lavapipe
5e8791a0bf0 : radeonsi: Fix dead lock with aux_context_lock in si_screen_clear_buffer.
90e42f87ac5 : add one last 20.1 release to coincide with expected 20.2.1
fe16e409748 : docs: update calendar and link releases notes for 20.1.9
00d87db89b5 : docs: add release notes for 20.1.9
49ec863e830 : freedreno/ir3: Enable the i/o vectorizer on UBOs.
e3f46558051 : nir: Make nir_lower_ubo_vec4() handle non-vec4-aligned loads.
618556a8cbd : nir: Drop the high_offset argument to the load_store_vectorizer filter.
5f757bb95c2 : nir: Make the load_store_vectorizer provide align_mul + align_offset.
9c5a793dc72 : nir/gl_nir_lower_buffers: Set up align_mul/offset on UBOs.
ffbfc1ec0eb : nir/nir_lower_uniforms_to_ubo: Set better alignments on our new instructions.
c88c89ff3ea : nir: Print the alignment information on casts.
6c1c5714409 : nir: Document a bit about how align_mul/offset work.
bd60e31c837 : freedreno/ir3: Make sure we run the opt loop after lowering UBOs to vec4.
8dc8922af25 : turnip: implement legacy API functions separately
25ebd7f90f8 : Revert "nir/lower_goto_if: Add a route::outside set"
57c9fc3cbaf : nir/lower_goto_ifs: Always include level dom_frontiers in prev_frontier
7749983658e : nir/lower_goto_ifs: Add asserts for SSA forks
dc010cb74e1 : nir/lower_goto_ifs: Use rzalloc
fa3c38ceb36 : spirv: Only run repair_ssa if structured
719c68016a2 : nir/dominance: Use _mesa_set_clear instead ofhand-rolling it
b6a4172f104 : nir/lower_goto_ifs: Don't destroy SSA form in the process
6f134a622b1 : nir/validate: Improve the validation of blocks
4fb2eddfdf9 : gallium/util: remove empty file u_half.h
7a1deb16f8a : gallium/util: remove redundant util_float_to_half_rtz
2b6a1723437 : util: remove util_float_to_half and util_half_to_float wrappers
5af81393e41 : util: move util_half_to_float code into _mesa_half_to_float_slow
87900afe5bb : util: implement f16c - fast half<->float conversions
7dbb1f74624 : nir/cf: Better handle intra-block splits
5e2e882270c : nir: Disallow goto and goto_if in clone and [de]serialize
9a48ed84ecd : nir/copy_propagate: Copy-prop into jump conditions
7f0cd6f1539 : nir/opt_if: Use early returns in opt_if_merge()
656e428ff4e : nir/opt_if: Remove open-coded nir_ssa_def_rewrite_uses()
c6f871b62e2 : nir/lower_returns: Use nir control flow insertion helpers
f103bded0b5 : ttn: Use nir control flow insertion helpers
f504eb683d8 : radv: Use nir control flow insertion helpers
b2ede6280c0 : intel/nir: Use nir control flow helpers
55e2b3424de : radeonsi: Fix imports with displayable DCC.
636f7702335 : bin/gen_release_notes.py: escape special rST characters
ae7975ecd43 : docs: cpu -> CPU
5fe6124661d : docs: Sandybridge -> Sandy Bridge
302fc318473 : docs: vmware -> VMWare
37bb6ddcc25 : docs: ubuntu -> Ubuntu
0c90662dfba : docs: scons -> SCons
7f4f441465a : docs: quote "git log"
50e26e5376e : docs: git -> Git
24e8e53bac3 : docs: android -> Android
ca613a5a7ef : docs: drm -> DRM
9f59b19ad04 : docs: wayland -> Wayland
8d2090e79d0 : docs: x11 -> X11
0db015294ea : docs: cmake -> CMake
b8b0e5ece02 : docs: gpu -> GPU
12d925dc8d6 : docs: visual studio -> Visual Studio
0e9d87eacc5 : docs: windows -> Windows
0df19e3c6bf : docs: linux -> Linux
557ee09c2ea : docs: microsoft -> Microsoft
d84420f5136 : docs: mingw -> MinGW
a14d64757b3 : docs: ninja -> Ninja
eb1e7e61e52 : docs: chocolatey -> Chocolatey
0732efbda91 : docs: mako -> Mako
fafd1f44257 : docs: bison -> Bison
1e75294e827 : docs: flex -> Flex
d95e2e48a9b : docs: python3 -> Python 3
e198fb64e10 : docs: meson -> Meson
0835ee9e8da : docs: correct reference to meson.build
5ed6432eebb : docs: llvm -> LLVM
a1904c96f3b : docs: bpp -> BPP
647a8283674 : docs: webservice -> web service
648cf633437 : docs: existant -> existent
766705d03b9 : docs: softwara -> software
92a594b1540 : spirv: Delete the legacy offset/index UBO/SSBO lowering
1cadbe51413 : vallium: Stop using lower_ubo_ssbo_access_to_offsets
657d49a9ba1 : spirv: Use derefs for push constants
d3fa7451a66 : anv,radv,tu,val: Call nir_lower_io for push constants
ac7537f155b : nir/lower_io: Add support for push constants
7a2b4ce22e4 : nir: Allow creating variables with nir_var_mem_push_const.
b0504ed682f : llvmpipe: use an alternate env var to enable clover.
760ba65733d : gallivm/nir: handle non-32-bit mul high
5d4502c0855 : gallivm/nir: fix up non 32-bit load stores
28911360507 : gallivm: fix 64-bit CL intrinsics.
728061b9689 : turnip: signal fence and semaphore in AcquireNextImage2KHR
e192f8f30a9 : turnip: share code between semaphores/fences + fence import/export
0497c9cb6cc : turnip: remove remaining uses of drmSyncobj helpers
c4d5010c54d : turnip: rework ImportSemaphoreFdKHR
8343c32f5af : turnip: rework GetSemaphoreFdKHR
fb76af24a22 : turnip: semaphores simplification (only syncobj semaphores supported)
1dfb5a93d26 : turnip: set MSM_SUBMIT_SYNCOBJ_RESET for submit pWaitSemaphores
2a3f6e0267f : turnip: always create permanent syncobj for semaphore
dcc278c7227 : turnip: clean up tu_device_memory
d12cdc9374d : gallivm: fix pow(0, y) to be 0
89a1a3e9d60 : r600/sfn: extend life range of all variables by one
02245e38fcf : r600/sfn: Add support for more barrier instructions
48edb98a7ef : r600/sfn: Fix IDX register ID
7683e275619 : r600/sfn: Fix enabling the right interpolator for inerpolate_at_sample
16a3a563212 : freedreno: Don't leak LRZ bo's
7454ae4ea65 : freedreno/registers: Add a couple things used on kernel side
27c8d976577 : freedreno/drm: Also clean ring_cache
98093e2780e : freedreno/a6xx: Small cleanup
5be3cfdc13e : freedreno: Don't leak border_color_buf reference
69a3ef65112 : freedreno/drm: drop bo's dev reference
6a20c630b93 : zink: unify all occurrences of waiting on a fence
e31381ac260 : zink: combine all surface layout-setting for src/dst into util function
24f19f409d3 : radv: Write correct dispatch size for RGP.
1b39d74c682 : ci: Enable remaining (non-rotate) mustpass CTS tests
8abe3bb95a8 : ci: cherry-pick deqp fix for config choosing
aee1c08c065 : ci/deqp-runner: Allow overriding width/height/config
efaea653b57 : intel: Add support for i945g to intel_stub_gpu.
f5901484a77 : Add driver override to envvars.rst
2584d48b2cf : gallium/vl: add chroma_format arg to vl_video_buffer functions
b121b1b8b8f : gallium/vl: do not call transfer_unmap if transfer is NULL
8d2757789a7 : tu: Enable multi-position output
64ad5a1f7b3 : ir3, tu: Link per-view position correctly
6982e8510b5 : ir3, tu: Run optimization loop twice
41a5a218582 : tu: Refactor shader compilation flow
67ac16611bd : tu: Write multiview control registers in binning pass
a3363c348dc : gallium: Make pipe_viewport_state swizzle_x/y/z/w bit-fields 8 bits wide
291cfb1e415 : radv: move lowering of FS outputs outside of ACO
4dae9e53f6a : radv: call nir_io_add_const_offset_to_base for FS outputs
85074ec5f6c : radv/aco: Set I/O variable locations outside ACO.
cd1fab4ed67 : radeonsi: enable support for GL_NV_shader_atomic_int64
40c1f9883e5 : mesa,glsl: add support for GL_NV_shader_atomic_int64
8930b3bcdd8 : gallium: prepare framework for supporting GL_NV_shader_atomic_int64
6d4f33e469b : turnip: initial implementation of VK_KHR_push_descriptor
992d24794da : turnip: delete unused/broken pipeline layout hashing code
560cff81f58 : turnip: remove unused cmd_buffer/device arguments in descriptor sets
d4d5382963f : panfrost: Add support for rbg16 formats
dfc1d54b5b6 : CI: Re-enable Panfrost T7xx
51e2b310397 : nir: Handle per-view io in nir_io_add_const_offset_to_base()
bc8a5c07522 : nir: Add per_view to IO semantics
5a88db682e0 : nir/lower_io_arrays: Fix xfb_offset bug
df955ce6b6a : nir: Count i/o slots correctly for per-view variables
a9b2ac854f5 : anv: Use nir_lower_multiview pass
ffe946d7e82 : nir: Add nir_lower_multiview pass
b4c07a8a87d : gallium/util: allow scaling blits for stencil-fallback
69654f0918f : gallium/util: fix texture-coordinates for stencil-fallback
a21e1e615cd : gallium/util: set right dst-dimensions
778fe02f3b9 : radv/llvm: call nir_lower_io_to_vector with FS to fix array tests
2c08404f388 : docs: add INTEL_SHADER_ASM_READ_PATH description
1a19fae8680 : radeonsi: call nir_io_add_const_offset_to_base only once per shader
a0e35c7562e : nir/lower_io: change nir_io_add_const_offset_to_base to use bitfield modes
7685c37bf47 : st/mesa: use roundf instead of floorf for lod-bias rounding
8f24a14175b : docs: gallium -> Gallium
9d34c99f39a : docs: docker -> Docker
8a5eebd4090 : docs: debian -> Debian
40cb54270cd : docs: flavours -> flavors
915d4e28068 : docs: stabilisation -> stabilization
6ec9a7ec57e : docs: consistantly -> consistently
b1874a26952 : docs: clippping -> clipping
af9b073d5f7 : docs: drop outdated gallium-docs comment
cff7de4bb59 : kmsro: Add mediatek entry point
fefb3e9b700 : panfrost: Add preliminary support for Mali G72
c420db1665b : panfrost: Adjust quirks for bifrost v6
89e3c3a8261 : mesa: bptc fixes for decompress rgba_unorm and rgb_float
1b4d968106d : ac/llvm: fix invalid IR if image stores are shrinked using the format
1588644543d : radv: lower deref operations for global memory for both backends
10b73e2b522 : ac/nir: implement nir_intrinsic_global_atomic_*
82cf6075572 : ac/nir: implement nir_intrinsic_{load,store}_global
f01656c4959 : CI: Temporarily disable Panfrost T7xx
62ba074ff51 : pan/mdg: Fix memory leak on error path.
287ef94e242 : gallium/swr: Remove unreachable code.
70945dd3629 : aco: Initialize mad_info member literal_idx.
93b8cdfe8bf : anv: Check file descriptor before closing.
1d71b1a3112 : intel/vec4: Remove everything related to VS_OPCODE_SET_SIMD4X2_HEADER_GEN9
2a49007411b : intel/vec4: Remove all support for Gen8+ [v2]
60e1d0f0286 : intel/compiler: Remove INTEL_SCALAR_... env variables
d0ce24c8caa : intel/vec4: Remove inline lowering of LRP
86bab92aa4a : intel/compiler: Don't fallback to vec4 when scalar GS compile fails [v2]
92f08860c97 : intel/compiler: Silence unused parameter warning in brw_surface_payload_size
9bcdca2455e : intel/vec4: Silence unused paramter warnings in brw_vec4_generator.cpp
bc32d41a9b6 : r600/sfn: Add support for helper invocations
6aa196b673e : r600/sfn: remove old code to track uniforms as it is no longer needed
31e42fb780f : r600/sfn: replace hand-backed literal check by NIR function
6784cea646b : r600/sfn; go back to not lowering uniforms to UBOs
9a6b11a7330 : r600/sfn: Fix indirect const buffer access
73c5f451916 : r600/sfn: Fix interpolate at sample
a8435f70ed5 : r600/sfn: use fine gradient evaluation for interpolate_at_offset
8540523610e : r600/sfn: save some instructions when doing multisample on sample 0
0c5dfd294aa : r600/sfn: Support group memory barrier
972dd730d92 : r600/sfn: lower to scalar for some optimizations and vectortize later
d55404b39cb : r600/sfn: Handle nir_op_b2b32
b2df9c2f886 : r600/sfn: Fix emitting shared atomics with constant sources
e8c5f8b9d32 : nir/lower_clip: Add i/o semantics for load/store intrinsics.
4ed904989fc : ci/freedreno: Add trace tests for glxgears, 0 A.D., and xonotic.
8538b7d270a : ci/freedreno: Sort the traces in the .yml of expectations
a55dc276a38 : turnip: Replace tu_log*() with mesa_log*()
13ea7db760b : mesa: Promote Intel's simple logging façade for Android to util/
78165ea3e20 : radv: Record cache flushes for RGP.
cc731821527 : radv: Include flushes in the barrier.
eff6710aabb : radv: Fix RGP Asic CU info for GFX10+.
8349b820831 : radv: Use correct alignment for SQTT buffer sizes.
929aac5d350 : radv: Fix emitting SQTT userdata.
b2d042b6210 : zink: remove old extension infrastructure
08d51e92aee : zink: use the new, generated extension infrastructure
79c0023d196 : zink: use the new extension infrastructure in device creation
0ed17a212c7 : zink: hook zink_device_info.py to build system
f1432fd3e2d : zink: generate extension infrastructure using a python script
39098a2053d : nir/lower_memory_model: do not break with global atomic operations
de1409089c7 : nir/lower_memory_model: return progress when visiting instructions
756441b2979 : pan/mdg: Infer whether to disassemble shaders from info.internal
90eaaada0d1 : panfrost: Mark blit shaders as internal
ee073cb543e : nir/load_store_vectorize: improve vectorization with identical operations
d9c4ec91542 : panfrost: Remove extra printf arguments.
f2b94ae085a : glsl/linker: Add support for XFB varying lowering in geometry shader
5bea0e88ba0 : docs: recognisable -> recognizable
b8f1075c4e7 : docs: url -> URL
7ee8a3a2cbc : docs: gitlab -> GitLab
0894b590a45 : docs: initialisation -> initialization
2dccdb1d4b3 : docs: timeplan -> time plan
9890927a84d : docs: behaviour -> behavior
33180434afc : docs: unecessarily -> unnecessarily
fa834fd3653 : docs: make two acronyms upper-case
58512ce3dcb : docs: frambuffer -> framebuffer
e8c1b789aad : docs: scons -> SCons
3fffa27a3bb : docs: apis -> APIs
255019340c5 : docs: everytime -> every time
e48b77b5b14 : docs: remove webmaster article
d2dfbf0e66b : docs: store prefixes in redirects
12760d0480d : docs: show 'Edit on GitLab'-link
96ac7115dbd : docs: escape backquote character
92831412d95 : lima: set clear depth value to 0x00ffffff as default
9a221095d27 : android: pan/bi: fix typo in bifrost_gen_disasm.c gen rules
2e9599b34d1 : panfrost: Fix bifrost tiler job emission
6abb4cd8b9d : panfrost: Fix bifrost tiler descriptor definition
4017116fa04 : ci: add dEQP-VK.info.device_extensions to the list of skipped tests
a3543adc262 : clover: set LLVM min version to 8.0.1
bf80fb7c309 : clover/nir: Call the memcpy lowering pass
8323c03bbfd : spirv: Add support for OpCopyMemorySized
a3177cca996 : nir: Add a lowering pass to lower memcpy
b2899f72657 : nir: Add a new memcpy intrinsic
8cbb6640f0e : spirv: Use the new types helpers
de295b61da3 : compiler/types: Add glsl_baseN_t_type(bit_size) helpers
4cb6a8d2dee : gallivm: add support for lowered IO in vertex shaders
465460943a2 : meson/anv: Use variable that checks for --build-id
5f1855d896c : vtn/opencl: Switch fma to conditionally use libclc for 32bit floats
8fb25c48a40 : vtn/opencl: Only use libclc ldexp when lower_ldexp is set
09bca4cb957 : vtn/opencl: Switch some nir-sequence ops to use libclc
03fd217d219 : vtn/opencl: Switch division-related ops to use libclc
2624faf1379 : vtn/opencl: Switch exp/pow/log to use libclc
4cc9ad4eeb4 : vtn/opencl: Switch non-native trig to use libclc
6aee49578fb : vtn/opencl: Hook up OpenCL async copy and group wait opcodes via libclc
00261d883dd : vtn/opencl: Rework handle_instr to be able to handle core SPIR-V opcodes via libclc
b08fd45be0c : vtn/opencl: Implement a lot of opcodes via libclc
f33b417652c : clover: handle libclc shader (v3)
14bc2dcaae0 : util: add missing extern C
6436e3ac189 : vtn/opencl: Add infrastructure for calling out to libclc
45d43ad2b8d : clover/nir: add libclc lowering pass
2013903bc24 : vtn/opencl: Rework type handling for CL extension opcodes
938be4d6fab : nir/vtn: Add handling for SPIR-V event variables
c9a6b94f9ea : vtn: add an option to create a nir library from spirv
2826a5a9232 : nir: Add glsl_base_type unsigned -> signed version helper
93db59e0664 : nir: Add an internal flag to shader_info
b4a087ce1b9 : driconf: Use nesting macros for defining options.
e5d2481bfe7 : virgl: Clean up the driconf definition of GLES_SAMPLES_PASSED_VALUE.
1eb79dfaded : util/xmlconfig: Add a unit test of the code.
7f3e881c6cd : blorp: Ensure aligned HIZ_CCS_WT partial clears
7898993bcd5 : meson: add support for loongson's mips/mips64 arch.
b54a0bb5283 : freedreno/layout: add tile_all flag to the layout
0206fb39418 : nir/liveness: Consider if uses in nir_ssa_defs_interfere
dcba32bac08 : turnip: implement VK_EXT_extended_dynamic_state
b2fa2d99ae2 : turnip: move A6XX_RB_ALPHA_CONTROL write to init_hw
d1588c78abd : turnip: fix wrong indentation in tu6_draw_common
a18c84ecce3 : nir/instr_set: hash intrinsic sources
b8c31ac06d3 : lima: fix glCopyTexSubImage2D
7b9cf779f27 : kmsro: Extend to include imx-dcss
77486db867b : intel/fs: Disable sample mask predication for scratch stores
cbef2dc7d3c : zink: only set stencil-ref for back if two-sided
4b2525b68df : zink: store base-object of DSA-state
9e94dcca67a : zink: correct typo in stencil-setup
d1d27e9db49 : radeonsi: remove redundant info.uses_fbfetch
7b1e01fec72 : radeonsi: remove redundant variables from struct si_compute
16afaf03555 : radeonsi: assume that constant load_local_group_size has been optimized out
0492adaca73 : radeonsi: run NIR optimizations that glsl_to_nir runs but other places might not
8a1d556c5af : radeonsi: get input/output usage flags from shader_info directly
0280cc75ba4 : radeonsi: get information about FS color outputs from shader_info directly
343e5caa750 : radeonsi: use info.system_values_read
cce3556abdb : radeonsi: call nir_shader_gather_info after lowering and optimizing NIR
8be46d6558e : radeonsi: fix indirect dispatches with variable block sizes
a7e3cc7a0ea : etnaviv: simplify linear stride implementation
f7583bda8f0 : ci: Extend meson-clang coverage by compiling all gallium drivers
1dd4505bc1e : panfrost: gen_pack: Fix gnu-empty-initializer errors
ea77958fea2 : nir: gather information about fbfetch and dual source color
a6abf175ef3 : nir: fix input/output info gathering for lowered IO
ef98c175c01 : nir: gather fs.uses_sample_qualifier from lowered IO
7b108e6ac40 : nir: set system_values_read for all intrinsics
abe9588ff04 : nir: gather tess.tcs_cross_invocation info from lowered IO intrinsics
10be706778b : nir: gather indirect info from lowered IO intrinsics
3173367a478 : spirv: vtn_fail with a nice message on unsupported rounding modes
03e7b75c22c : gallium/dri2: Move image->texture assignment after image NULL check.
4bd0df0e4a8 : r600/sfn: Initialize GPRValue member m_pin_to_channel.
974981c4e6b : gallium/drm: Make the pipe loader handle the driconf merging.
87392385b59 : gallium/drm: Define the DRM entrypoints in drm_helper.h
bc10b4968e8 : gallium/drm: Refactor the stub screen create functions.
9ec28b8d226 : gallium/drm: Deduplicate screen creation for the dynamic (clover) pipe loader.
472a20c5fc0 : radeonsi: Only call nir_lower_var_copies at the end of the opt loop
7971918924d : zink: reorder create_stream_output_target to fix failure case leak
bc5c0433be8 : zink: apply viewport count when creating pipelines
cc939fe9b70 : zink: correctly set up fb-sized scissors for each viewport
8a2ddcb4a94 : zink: set multiviewport cap in ntv when gl_ViewportIndex is a written output
09be30b9e4c : zink: move viewport count to zink_gfx_pipeline_state
818bd610992 : zink: implement ARB_instanced_arrays
00515517016 : zink: verify that src and dst aspects are the same in resource_copy_region hook
6feec2d40e0 : zink: clamp min created fb size to 1x1
9ce1e99913d : zink: use correct layer count when creating framebuffer
e30367a2736 : zink: use correct number of samples on framebuffer in set_framebuffer_state
f6c87216d31 : zink: use correct value for color buffer sample count when creating renderpass
140f53e6464 : Revert "nir: replace lower_ffma and fuse_ffma with has_ffma"
d8cdcd4adf7 : radv: use syncobj for wsi fence
1aa1b9f86ce : radv: fix incorrect ResetFences path for WSI fence
90b98c06493 : amd/tmz: move uses_secure_bos to radeon_winsys
24796899685 : radeonsi/tmz: add workaround for mpv/vaapi subtitles
2c6643546ad : radeonsi/tmz: add a tmz variant for sctx::eop_bug_scratch
133895574c9 : radeonsi: disable primitive discard if tmz is in use
8e2768bbfb1 : radeonsi/tmz: add tmz variant for sctx::tess_rings
2589888ce96 : radeonsi/tmz: add tmz variant of sctx::wait_mem_scratch
de088daccc2 : radeonsi/tmz: fail si_texture_transfer_map if tex is encrypted
55b018b634b : amd/winsys: add RADEON_FLUSH_TOGGLE_SECURE_SUBMISSION
1b0d660cbc7 : radeonsi/tmz: allow secure job if the app made a tmz allocation
f5ec6176774 : ac/gpu_info: add detection of TMZ support
846e3931428 : amd: add AMDGPU_IDS_FLAGS_TMZ definition to amdgpu_drm.h
5e4aecec932 : radeonsi: introduce SI_RESOURCE_FLAG_INTERNAL / RADEON_FLAG_DRIVER_INTERNAL
131412cc4d0 : radeonsi/tmz: allocate depth/stencil buffers as encrypted
0a59d2a3e9e : radeonsi/tmz: add safety assert when tmz is enabled
59b267dea45 : radeonsi/tmz: use secure job if using an encrypted z/s buffer
5bc24fe2833 : radeonsi/tmz: use secure job if framebuffer has dcc
cec0bc73e55 : turnip: rework fences to use syncobjs
c23206757a1 : turnip: require syncobj support
89ffe859a8f : turnip: add a fd field to tu_device
ec4fe92c834 : turnip: delete unused tu_fence_signal function
9e13a16c974 : mesa: handle GL_FRONT after translating to it
005d9d22190 : ci: adjust RadeonSI rules
4c71cda9abc : vulkan/wsi/display: add option for display fence to signal syncobj
32d754825c4 : radeonsi: always inline draw-related functions that have only one use
f24b5894f8c : radeonsi: lift the conditional for skipping si_upload_vertex_buffer_descriptors
0b2f75f9ac2 : radeonsi: add unlikely statements into si_draw_vbo
8ab15c9e33a : radeonsi: move si_upload_vertex_buffer_descriptors into si_state_draw.c
12b1e8a35d2 : radeonsi: reorganize the code around the gfx9 scissor bug
532259b8a3b : radeonsi: don't call emit_cache_flush after uploading bindless descriptors
d647065b069 : radeonsi: move a displaced comment in si_draw_vbo
816a867bbd0 : radeonsi: call si_upload_graphics_shader_descriptors before the big conditional
0051f2cb2a6 : radeonsi: use optimal order of operations when setting up a compute dispatch
e560028c8e7 : panfrost: Remove redundant casts of viewport position
3d0ae7a9dab : panfrost: Handle non-positive viewport positions
2aa48bb5a8d : panfrost: Clamp uniform buffer size
939ddf3f67d : nir: replace lower_ffma and fuse_ffma with has_ffma
f1284505f0f : radeonsi: fuse or lower ffma optimally on all chips
771aad30276 : nir: split lower_ffma into lower_ffma16/32/64
21174dedec4 : nir: split fuse_ffma into fuse_ffma16/32/64
c58b46edf0e : radeonsi: force linear for textures with height=1 (gfx6-8)
5f27777379f : radeonsi: add a tweak for PS wave CU utilization for gfx10.3
b5debe180ef : radeonsi: break a binning batch on a new PS if bins can use multiple state sets
972fb0368cb : radeonsi: move binning parameters into si_screen
8b134fb915d : radeonsi: set KEEP_TOGETHER_ENABLE if needed
28a76161e5d : pan/bi: Remove old register mode definitions
7a0f3b607ed : pan/bi: Use canonical register packing
514da97ccac : pan/bi: Rename port -> slot
c749803dbbe : pan/bi: Decode all 32-bit register modes
bdb33f75297 : pan/bi: Pass 'first' through disassembler
4d3d5a66c92 : pan/bi: Add bifrost_reg_mode enum
b392c079834 : pan/bi: Disassemble PC-relative addresses
08a9e5e3e89 : pan/bi: Decode M values in disasm
9de34e16e0e : pan/bi: Track M values of disassembled constants
43c6623c9eb : pan/bi: Inline dump_instr
5ff3feab88a : pan/bi: Annotate disassemble with format names
ab5cc3e717d : pan/bi: Annotate stop bit (canonically "Z-bit")
24a74b352c8 : radv: add a tweak for PS wave CU utilization for gfx10.3
6865a6a74cf : radv: set KEEP_TOGETHER_ENABLE if necessary on GFX10+
68bb91ee111 : radeonsi: don't use nir_opt_access
87f91e20143 : st/nir: call nir_opt_access before gl_nir_lower_buffers
e893102bcf5 : radv: Add VK_FORMAT_E5B9G9R9_UFLOAT_PACK32 rendering support.
43735c06df4 : radv: Simplify radv_is_hw_resolve_pipeline.
bf0c82b7f8c : radv: Disable NGG on APUs.
12128fb1351 : lima: add natively supported vertex buffer formats
c669db0b503 : radv: advertise VK_KHR_copy_commands2
0401507b77d : radv: add support for CmdResolveImage2KHR()
9a700af65cf : radv: cleanup selecting the hardware resolve path
fe819710adc : radv: add support for CmdCopyImageToBuffer2KHR()
f9915ac465b : radv: add support for CmdCopyImage2KHR()
69dfcfbb24a : radv: add support for CmdCopyBufferToImage2KHR()
22a08da7370 : radv: add support for CmdCopyBuffer2KHR()
eccc73ff780 : radv: add support for CmdBlitImage2KHR()
cc709a07f27 : radv: add VK_KHR_copy_commands2 but leave it disabled
93f158fa2ea : radv: bump the advertised patch version to 145
43c7de6b910 : radv: remove useless assignment of MAX_API_VERSION
e8a40715a8b : gallium/util: add blitter-support for stencil-fallback
2970d388a2a : gallium/util: add shader for stencil-blits
924e27647e4 : nir_lower_system_values: Fix load_global_invocation_id to use base_work_group_id even with no base_global id
ee4cee6dbdf : android: Disable trying to read/write to the disk cache.
25b36d900ac : mesa: Make the android_stub be a set of non-installed shared libraries.
283686ad676 : amd: add VanGogh support
d7495bd123a : amd: add Dimgrey Cavefish support
40a50e93985 : radeonsi: remove KILL_PS_INF_INTERP/CLAMP_DIV_BY_ZERO, use screen::options
98188409d11 : radeonsi: move debug options from si_disk_cache_create to si_get_ir_cache_key
cd12fcff96c : radeonsi: set TRUNC_COORD=0 for Total War: WARHAMMER to fix it
a1f46d7b694 : ci: Use ignore_scheduled_pipelines anchor in .radeonsi-rules
e781cc70255 : tu: Expose shaderStorageImage*WithoutFormat
37054a3ef5d : ir3: Don't use the format to get the image type
6ebc20fd884 : tu: Expose shaderImageGatherExtended
205f4e9a577 : tu: Expose shaderStorageImageExtendedFormats
5d3a72cd617 : r600/sfn: Be a bit more verbose when logging skipped FS outputs
2abb9e5ac09 : r600/sfn: Acquire the number of FS outputs and the write_all info early
c2c5f71e962 : r600/sfn: Take dual source blending output indices into account
44b45a38649 : r600/sfn: Handle number of color outputs taking dual source blending into account
234891cc042 : r600/sfn: Keep info about dual-source blend in FS
0a59530d0db : r600/sfn: Sort the outputs of the FS according to data index
a57f2d0cfab : r600: Add flag for dual-source blending to shader key
1625a9b9ae2 : r600/sfn: remove a useless if-condition
4f4e90bfbb9 : r600/sfn: run late algebraic optimizations
8a9876a29ad : r600/sfn: use cnde instead of cnde_int
952cf95f8b0 : etnaviv: fix comment for source of etna_mesa_debug
9750164c093 : nir: Rename get_buffer_size to get_ssbo_size
f100cf0d30e : aco: stop multiplying driver_location by 4
fd872c3cf77 : aco: remove dead indirect fs input loading
7f51a0c6705 : aco: use nir's constant source helpers more
430cc90071e : aco: use nir_get_io_offset_src() in visit_load_input()
9bba79088da : aco: use io semantics to get an intrinsic's slot
d58a1a87cca : aco: Use NIR IO semantics for tess factor IO locations.
10540c2f6ff : anv: implement VK_KHR_copy_commands2
4c1c546fa34 : vulkan: bump headers/registry to 1.2.154
f2b17dec120 : nir/lower_samplers: Clamp out-of-bounds access to array of samplers
0ba82f78a57 : nir/large_constants: Eliminate out-of-bounds writes to large constants
66669eb5295 : nir/lower_io: Eliminate oob writes and return zero for oob reads
8e1193b8d37 : radeon: rename RADEON_TRANSFER_* -> RADEON_MAP_*
31765340fd6 : gallium: rename transfer flags -> map flags in comments
35860685576 : gallium: rename pipe_transfer_usage -> pipe_map_flags
22253e6b650 : gallium: rename PIPE_TRANSFER_* -> PIPE_MAP_*
44f1b1be7a3 : radeonsi: add 16-bit ALU vectorization
6702e542cf1 : radeonsi: don't scalarize 16-bit vec2 ALU opcodes
e823742e9fd : radeonsi: vectorize IO for better ALU vectorization
98a52fecdaa : radeonsi: implement 16-bit FS color outputs
d3c63d6f606 : radeonsi: set flags for FP16 in shaders
c5277f035ed : radeonsi: don't lower pack for better 16-bit vectorization
581a3516dc1 : ac/nir: implement nir_op_[un]pack_[64/32]_*
3022cf3bac5 : glsl: Initialize ir_constant member const_elements in all constructors.
a5967f308ca : pan/bi: Fix typo.
ade72e677b3 : st/mesa: Deal with empty textures/buffers in semaphore wait/signal.
08add9f61c9 : turnip/kgsl: Associate fences with submits.
e80758405c7 : turnip: Add kgsl backend
cc3bf00cc26 : intel/compiler: fixup Gen12 workaround for array sizes
54b9013e4c8 : wsi/x11: Create a present queue for VK_PRESENT_MODE_FIFO_RELAXED_KHR
26a83bef7b9 : gallium/auxiliary/vl: Include src region in scale_y calculation
9a4daac0bbf : frontends/va: Enabled packed headers for H.264 encoder
7b9414f23f3 : radeon: Pass HEVC encode crop parameters to the encoder
245f619411b : gallium: Parse packed HEVC SPS encode header for crop parameters
0a3f92bcc66 : r600/sfn: Fix typo in comment
07cb38f0d2f : r600/sfn: Fix component count for fdph
eb3199db3e5 : r600/sfn: make number of source components a local variable
d78e7b7aee8 : gallium/auxiliary/vl: Odd Dimensions are failing
05b6612b4ec : radv: do not lower UBO/SSBO access to offsets
3808fa40b4e : radv: add a helper for loading meta descriptors
0836e90418e : ci: Don't create test-docs job if the pages one exists in the pipeline
efec576405d : ci: Prevent pages job from running in pre-merge pipelines
8cb450f769b : ci: Always use CI_PROJECT_NAMESPACE instead of CI_PROJECT_PATH
208876b7092 : ci: Add "is for Marge Bot" YAML anchor
0fcb8b33c57 : ci: Add "is pre-merge pipeline" YAML anchor
b47f1bbff98 : ci: Add "is post-merge pipeline" YAML anchor
22a7c252dc9 : ci: Add "is forked branch" YAML anchor
24f5329e2a5 : ci: Add "is forked branch or pre-merge pipeline" YAML anchor
a33026ee7c7 : ci: Add "is post-merge pipeline, not for Marge Bot" YAML anchor
f79ae945380 : ci: Add "is pre-merge pipeline for Marge Bot" YAML anchor
ac56d669927 : ci: Add "is master branch of main project" YAML anchor
c3ae82be247 : ci: Add "is scheduled pipeline" YAML anchor
2b99e15d0a6 : radv: fix transform feedback crashes if pCounterBufferOffsets is NULL
d2c18b7bf37 : aco: use bit vectors for liveness sets
ec2185c5984 : aco: keep track of temporaries' regclasses in the Program
f007115e3b9 : radeonsi: change vendor name to AMD
b73e165a04c : radeonsi: reduce PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE value
1826367333e : radeonsi: move GL vendor workaround to drirc
fc6df020e3b : gallium: add PIPE_CAP_MAX_TEXTURE_MB
2228835fb55 : radv,aco: fix reading primitive ID in FS after TES
b1c3f63b8da : panfrost: decode: Misc formatting improvements
6b923037726 : panfrost: Avoid copying job descriptors around when we can
d289209ea68 : panfrost: XML-ify the compute job descriptor
54d716a0342 : panfrost: Rename the Blend dither disable flag
89fafe9e926 : panfrost: XML-ify the fragment job descriptor
9121e7daaf7 : panfrost: XML-ify the write value job descriptor
eb923548c51 : panfrost: XML-ify the job header descriptor
5d5f7552a52 : panfrost: XML-ify the multi-target framebuffer descriptors
efce73d99d0 : panfrost: XML-ify the bifrost tiler descriptors
95eb7d9a343 : panfrost: XML-ify the single target framebuffer descriptor
e855698ddd1 : panfrost: XML-ify the midgard tiler descriptor
fb95729b695 : panfrost: Add Tiled linear mode to the Block Format enum
76096c723ae : panfrost: Clarify what TILED mode is
3a06fc3d345 : panfrost: XML-ify the local storage descriptor
706974ce173 : panfrost: decode: Use pan_{unpack,print}() when applicable
aa2670c7fb8 : panfrost: decode: Add a macro to dump unpacked descriptors
670e818f906 : panfrost: decode: Rework the DUMP_{CL,ADDR}() macros
6249ae79d38 : panfrost: decode: Make the indentation consistent with auto-generated print helpers
fd0941c5733 : panfrost: gen_pack: Allow enum/define values expressed in hexadecimal
51d5d44953e : panfrost: gen_pack: Add a log2 modifier
718b521f569 : panfrost: gen_pack: Add an align() modifier
1b27817f175 : panfrost: gen_pack: Allow empty structs
c7a10193d42 : panfrost: gen_pack: Add the aggregate concept
fa7d0974fb9 : panfrost: gen_pack: Move the group get_length() logic to its own method
62c0ef06c83 : panfrost: gen_pack: Add pan_{unpack,print}() helpers
ddd82c3ab8c : panfrost: gen_pack: Fix __gen_unpack_uint()
66f25dd210f : panfrost: gen_pack: Minor formatting improvement
2aa5838730f : Revert "panfrost: Drop implicit blend pooling"
8ae4cec95fa : Revert "radv: emit {CB,DB}_RMI_L2_CACHE_CONTROL at framebuffer time"
0a84c595c21 : Revert "radv: set BIG_PAGE to improve performance on GFX10.3"
d78df70c2a8 : radv,radeonsi: Disable compression on interop depth images
ecc19e9819c : ac/surface: Fix depth import on GFX6-GFX8.
f63ffc18e79 : intel/fs/swsb: SCHEDULING_FENCE only emits SYNC_NOP
e1fc23265f9 : nir: Add a pass for lowering CL-style image ops to texture ops
3fc425b3559 : spirv: Plumb access qualifiers through from image types
1e902102c49 : spirv: Access qualifiers are not a bitfield
afa5c2e9934 : clover: Pull the stride from pipe_transfer for image maps
27516baa2ae : pan/mdg: Use nir_shader_instructions_pass for fdot2 lowering
7a348b43f2a : pan/mdg: Use nir_shader_instructions_pass for nir_lod_errata
6064b8ee143 : pan/mdg: Return a bool from midgard_nir_lod_errata
7acf364131f : panfrost: Set modifier_constant to true for exported resources
95ee0ba41f0 : lima: fix vertex shader uniform buffer size
6a1926035bd : lima: allocate new bo for stream draw
017ca86b223 : radeonsi: Move display dcc dirty tracking to framebuffer emission.
c6c1fa9a263 : radeonsi: Put retile map in separate buffers.
be48cf804b3 : amd/common: Store non-displayable DCC pitch.
4656e682947 : radeonsi: fix user fence GPU address
9aa86eb61aa : glsl_type: Add packed to structure type comparison for hash map
7b4eaac6a9c : radv: fix vertex buffer null descriptors
ec13622ff4b : radv: fix null descriptor for dynamic buffers
090fc593b44 : mesa: fix glUniform* when a struct contains a bindless sampler
77af1ca690f : etnaviv: add disk cache
6a0d7f6316c : etnaviv: shuffle some variant fields
12b8ad8f21f : swr: fix _BitScanForward64 on unix
82c49a66c07 : swr: missing _BitScanForward64 on 32 bits win
5805f5ab016 : glsl: take EXT_gpu_shader4 in to account when adding round
cde5b86a88c : turnip: Release bo_mutex lock before potential error path.
ffbdbd631ad : panfrost: Delete debug allocated syncobj.
fcc506e5206 : radesonsi: Remove unsigned comparison to zero.
1b862716ddf : disk_cache: Fix filename leak on error path.
183ca88a91d : android: pan/bi: Use new packing
792b51713bf : android: pan/bi: Use new disassembler
d74fe471019 : glx: Allow depth-30 pbuffers to work without a depth-30 pixmap format
a163cba1e3a : anv: Fix the target_bo assertion in anv_reloc_list_add
85cc2950a04 : radv: initialize with expanded cmask if the destination layout needs it
6f2b6952bef : nir: remove ubo_r600 instrinsic since ubo_vec4 is used now
18e97817148 : r600/sfn: Use load_ubo_vec4 lowering pass
98eb00face9 : r600: enable lowering uniforms to UBO
4ac4cdb5bfe : aco: fix incorrect assertion in emit_vop3a_instruction()
207219d4356 : turnip: Add support for a615.
45bff4e9890 : util: Makefile.sources: Add disk_cache_os.{c,h}
2aaa1564ad0 : nir/lower_io: don't reduce range if parent length is zero
a51aa6feb4d : pan/bi: Drop *FMIN reference
865e252dd01 : pan/bi: Remove unused packing data structures
ec43629e8c0 : pan/bi: Remove unused prints
2ff53879f21 : pan/bi: Use new packing
3fadd823461 : pan/bi: Move packing helpers to dedicated file
d2158a5b301 : pan/bi: Use src1/dest_invert instead of src_invert[]
08b105d7825 : pan/bi: Use 8-bit shifts
3d63a476f7a : pan/bi: Pass blend descriptor explicitly in IR
67d89568af2 : pan/bi: Track compute_lod in IR
8dd3a81c1d7 : pan/bi: Add format field to IR
6f5b78874ab : pan/bi: Introduce segments into the IR
33710ff8953 : pan/bi: Add dummy carry/borrow argument for iadd/isub
42ec4aa4785 : pan/bi: Use canonical syntax for special constants
5a569d09f42 : pan/bi: Use canonical syntax for registers/uniforms/imms
f8fc21059f3 : pan/bi: Use new disassembler
deab75250c5 : pan/bi: Export dump_src
05041811ce5 : pan/bi: Add bi_disasm_dest_* helpers
944cb8bcba5 : pan/bi: Add disassembly prototypes
82f33155f6d : pan/bi: Add disassembler generator
cf8f79a9fcf : pan/bi: Add packing generator
58da316de7a : pan/bi: Add ISA parser
07a5ec83fb0 : pan/bi: Add XML describing the instruction set
2044b1fba5d : pan/bi: Lower flrp16
b75a92e2010 : anv: assert that the target bo is valid when adding a reloc list
355f241d415 : anv: improve error message when failing to open device path
203b9349216 : docs: update calendar and link releases notes for 20.1.8
fdff24d930d : docs: add release notes for 20.1.8
123bdb61cc0 : gallium+mesa/st: lower uniforms based on compiler flag instead of packed uniforms cap
feb463da637 : llvmpipe: set lower_uniform_to_ubo compiler flag
80cde3ad55c : intel/compiler: Set lower_uniform_to_ubo compiler flag
7ab804dbb46 : freedreno/ir3: set lower_uniforms_to_ubo compiler flag
b155b6869ca : radeonsi: set compiler flag lower_uniforms_to_ubo
2c9fee9b6ad : nir: Add option lower_uniforms_to_ubo
8939c642e06 : gallium/aux: remove unused u_blit.[ch]
9ba2365c6f8 : vc4: remove unused header
9992797e1b1 : v3d: remove unused header
39e7bc23dd0 : r600/sfn: Fix comparison with different signedness
2d6316cca40 : r600/sfn: more fixing of vec4 fetching
f46e04a1c4a : r600/sfn: Fix source swizzle for gradient queries
02581acd07a : r600/sfn: Fix bitfield ops and 2x16 split_y
dfa45e26e21 : r600/sfn: Fix split_alu_modifiers
e85c0bdda55 : r600/sfn: Lower *sign opcodes in nir
c22e0fb02dc : r600/sfn: avoid some copies
f2280e03e21 : r600/sfn: Fix ordering of tex param moves
daaa71924ad : r600/sfn: clone shader before lowering to registers and src/dest modifiers
09558ad84ee : r600/sfn: Fix loading vertex attributes
e46b2ad1270 : r600/sfn: correct ring op patching
688680decce : r600/nir: fetch sources and split uniforms before emittting alu instructions
85f39cab8bd : r600: revert disabling llvm draw
f1730bed8f0 : radeonsi: fix guardband handling for large values
c493bb9a570 : radeonsi: fix quant_mode selection for large negative values
7d853966df4 : radeon/vcn: set dec->bs_ptr = NULL on unmap
eb60849ea24 : r600/uvd: set dec->bs_ptr = NULL on unmap
15038fe621a : docs/release-calendar: update 20.2
babe86f6cf4 : docs: add another 20.1.x release to allow for more overlap with 20.2
fd990aa4de3 : docs/download: mention tarball GPG signatures and link to the keys
4790811d780 : Revert "radeonsi: move L2_CACHE_CONTROL registers into si_emit_framebuffer_state"
b23013db0aa : Revert "radeonsi: set BIG_PAGE fields on gfx10.3"
758ab39d25e : radeonsi: clean up ffma handling
57bf4c2028c : nir,radeonsi: move ffma fusing to late optimizations for better codegen
a3512ddfdf7 : st/mesa: don't enable NV_copy_depth_to_color if NIR doesn't support FP64
782016ea42b : libgl-gdi: Fix unused-variable warnings.
bf849b058b1 : spirv: Handle OpTypeOpaque
efff7342204 : turnip: multiViewport and VK_EXT_shader_viewport_index_layer
52534c3a865 : freedreno/ir3: add view_zero to shader key
e732750b160 : freedreno/ir3: allow layer/viewport output for VS/GS/DS
338745c6f4b : frontends/va: Derive image from interlaced buffers in some cases
fcb558321e6 : frontends/va: Derive image from interlaced buffers
8c7ca97d3e3 : frontends/va: Add support for NV12/P010/P016 to vaDeriveImage
7bfaeaa590d : aco: pass -fno-exceptions and -fno-rtti
51a6261d38b : iris: remove additional pipe control done before hiz for older gens
320d80f2cee : intel/genxml: make sure test assert are compiled in
c7719b8cfc4 : nv50/ir: Initialize Converter members.
e607477d7ca : freedreno: Check file descriptor before write.
50f1cd40767 : ac/llvm: Fix nonportable sizeof.
16e788416f0 : android: aco/isel: Move context initialization code to a dedicated file
f3150abe5ef : etnaviv: call nir_opt_shrink_vectors(..) in opt loop
b10f34a7856 : pan/bit: Fix unit tests
c4f518ce6a6 : pan/bit: Set d3d=true for CMP tests
322ddbd5383 : panfrost: Fix nonzero stencil mask on vertex/compute
f3109c45798 : turnip: avoid heap allocations in QueueSubmit when semaphores are used
00914e21799 : nir/algebraic: fold some nested comparisons with ball and bany
8a2a9e9bb88 : glsl: fix per_vertex_accumulator::fields size
26299c87f8c : aco: Add base argument to emit_mbcnt.
f3780e7b8cf : aco: Clean up emit_mbcnt.
efa1c760d15 : aco: Fix emit_boolean_exclusive_scan in wave32 mode.
12567de2be7 : glsl: mark some builtins with correct glsl(es) version check
4868ce1451f : lima: dont split vec3 unaligned load inputs
bea6290ca09 : turnip: device global bo list
20a4235c4c9 : anv, iris: Set MediaSamplerDOPClockGateEnable for gen12+
e3101c96bb6 : anv/image: Disable multi-layer CCS_E on TGL+
656d8edd9e1 : nir/opt_vectorize: don't lose exact and no_*_wrap flags
eceb4fb904b : freedreno: fix fence-fd leak
ef980ac0c1c : radeonsi: fix max syncobj wait timeout
3182209673f : v3d/compiler: fix V3D double-rounding of .8 fixed-point XY coordinates
367ac07efcc : disk_cache: move cache item loading code into disk_cache_load_item() helper
8598dc1a758 : disk_cache: add new OS specific helper disk_cache_evict_item()
7893dc405cd : disk_cache: move get_cache_file() to an OS specific helper
593ef166aed : disk_cache: create new helper for writing cache items to disk
b4a3a80403e : disk_cache: move evict_lru_item() to an OS specific helper
e1236470dc6 : disk_cache: move munmap into an OS specific helper
889356e731e : disk_cache: move index mmap into OS specific helper
62c43391183 : disk_cache: add disk_cache_enabled() helper
4339ecde35c : disk_cache: move cache dir generation into OS specific helper file
65d0fa0852e : nv50/ir: Remove duplicate mask assignment.
a2a330a4eda : nv50/ir: Add fallthrough statement.
50d335804fb : nir/algebraic: add late optimizations that optimize out mediump conversions (v3)
b86305bb573 : nir/algebraic: collapse conversion opcodes (many patterns)
cdd498bbe88 : nir: add new mediump opcodes f2[ui]mp, i2fmp, u2fmp
385b4dbc394 : nir: enforce 32-bit src type requirement for f2fmp and i2imp
3d3df8dbffd : nir: remove redundant opcode u2ump
26fc5e1f4a8 : nir/algebraic: expand existing 32-bit patterns to all bit sizes using loops
3c8934a644b : nir/algebraic: add flrp patterns for 16 and 64 bits
3064feb2350 : pan/mdg: Obey f2fmp size restriction in fuse_io_16
5cd62359586 : blorp: Drop trailing whitespace in blorp_clear.c
1eff389bd3e : blorp: Fix alignment test for HIZ_CCS_WT fast-clears
40f7afc1e97 : nir: fix lower_mediump_outputs to not require variables
c2ae39e0cea : nir: add mediump flag to IO semantics
5e9e4573835 : glx/dri3: Implement GLX_EXT_swap_control_tear
60ebeb4608a : glx: Implement GLX_EXT_swap_control for DRI2 and DRI3
b8239abdf86 : glx: Reject glXSwapIntervalMESA greater than INT_MAX
e648442ceb3 : glx: Collect all the non-applegl extensions in the GetProcAddress table
72a0f7496a7 : glx: Use GLX_FUNCTION2 only for actually aliased function names
77d25627933 : wsi/x11: Hook up VK_PRESENT_MODE_FIFO_RELAXED_KHR
2f62a44df0f : ci: do not build libdrm for vc4, reedreno and etnaviv
52becd39a59 : turnip: rework vertex buffers draw state handling
69e65b9cf08 : intel/tools: fix possible randomly increased verbosity of error2aub
18eb853ac86 : intel/compiler: quiet Coverity warnings
5b6fd2a3140 : intel/tools: handle ftell errors
46a82aa3a60 : intel/tools: fix possible memory leak in the error path
5ea0b6a9c60 : intel/compiler: initialize remaining fields of various classes
40b964dc8f3 : intel/compiler: remove unused fs_validator::param_size
d3cd24999fd : anv: fix minor gen_ioctl(I915_PERF_IOCTL_CONFIG) error handling issue
265a3b9624f : driconf: add option to reuse GL names
a56849ddda6 : mesa: use _mesa_HashFindFreeKeys for GL functions
60ffadcbc07 : mesa: add _mesa_HashFindFreeKeys
fefc6d264a1 : mesa: add GL name reuse support
34852124db9 : mesa: add a isGenName parameter to _mesa_HashInsert
553d3719337 : util/idalloc: add lowest_free_idx to avoid iterating from 0
e808d382995 : util/idalloc: add util_idalloc_reserve
87ef970ee65 : mesa: move u_idalloc from gallium/aux/util to util
911ce374caf : freedreno/a6xx: Fix MSAA clear
6e4d0a48e3d : freedreno: Clear gs/tcs/tes state for clear blits
18f5d362829 : freedreno/a6xx: Fix fd6_draw_vbo() return
46edc08fe5a : freedreno/a6xx: Skip empty tile_setup
74f1c50dc3b : freedreno: Don't bypass fd_draw_vbo() in clear fallback
97e49b223ca : freedreno: Fix rast state for multisample clear
b0722cb6701 : gallivm: disable brilinear for lod bias and explicit lod.
cd4fb5a434c : freedreno/fdl: Add layout test for the Android CTS's MSAA mustpass surface.
14131ed3081 : freedreno/cffdec: Add support for texturator's 2DMS layout setup.
2f39727cc64 : freedreno/cffdec: Fix up texturator parsing scripts for XML changes.
bd647f8eb69 : freedreno: Add another new sysmem flake.
0bc36ef50e4 : spirv: Initialize spirv_test member shader.
2f61d7c22da : svga: Fix unused printf argument.
587969154f2 : freedreno: Fix file descriptor leak.
a4885d26915 : pan/mdg: Fix spilling of non-32-bit types
89401e58672 : nir: More NIR_MAX_VEC_COMPONENTS fixes
c5dd54e600b : nir/idiv_const: Use the modern nir_src_as_* constant helpers
d86e38af2c6 : nir: More NIR_MAX_VEC_COMPONENTS fixes
14b60ea302e : iris: Support I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS
dd215c83d04 : iris: Support MC modifier in plane count queries
80a8bb590ad : intel/common: Drop unused gen_aux_map_add_image
82720852bd6 : iris: Support planar resource imports for MC
1ddb1a6cf98 : intel/common: Add get_aux_map_format_bits()
c3c99f45718 : st/mesa: Don't map all P01X DRM formats to P016
9efd71466df : intel/isl: Add YUV format info for the aux-map
1ea3a54366c : intel/isl: Support ISL_AUX_USAGE_MC in surface states
e15543b71ad : intel/isl: Describe I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS
d686835171c : gallium/dri2: Support I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS import
a42bf9a2970 : gallium/dri2: Report I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS num_planes
7ee5da90edc : nir_dominance: Use uint32_t instead of int16_t for dominance counters
03eec294b90 : st/nir: Call st_glsl_to_nir_post_opts before interface unification
cdc025c9ef6 : mesa: Generate more errors from GetSamplerParameter
06c6920a5b1 : mesa: Fix GL_CLAMP handling in glSamplerParameter
0f61f0142ac : ci/bare-metal: Allow wget of the kernel/dtb for kernel development.
b4317fccdd7 : ci/bare-metal: Update the kernel to msm-next-pgtables
802d3611dce : turnip: Fix truncation of iovas to 32 bits in queries.
329c3172877 : turnip: Fix truncation of CS shader iovas to 32 bits.
3b3772d6e69 : freedreno: Make the pack struct have a .qword for wide addresses.
021523d4aea : turnip: Fix a compiler warning in release builds of the query code.
5a95cc04de6 : turnip: remove some unnecessary regs init
3d0ab65b48e : turnip: delete unused "tu_cmd_buffer_upload"
3b144d5fb85 : turnip: fix the type of tu_shader_module code field, delete unused sha1
6f511921696 : turnip: delete unused tu_image fields
bd53a255927 : turnip: delete tu_physical_device path field
e394ff9b5f8 : aco: fix validation of sub-dword parallel-copies
834b449a467 : aco: fix value numbering of reductions
5a8447cbd40 : aco: don't apply constant to SDWA on GFX8
29cb3cba9ff : aco: workaround disassembler bug of v_writelane_b32 with literal
36e58a14cc3 : aco: fix v_writelane_b32 with two sgprs
641d45befb4 : nir/opt_loop_unroll: fix is_access_out_of_bounds with vectors
c0d04cd5bbc : panfrost: AFBC to linear layout conversion
a3431ffb693 : panfrost: Move tiled-linear conversion checking to a new function
c3564532059 : panfrost: Seperate resource setup and bo creation
23ad95227a8 : panfrost: Correctly set modifier_constant
361396c8668 : panfrost: Remove old comment on broken depth reload
5857a015b5e : panfrost: Cleanup panfrost_get_param
811b9cb53fa : docs/features: Add missing Panfrost extensions
cf2eebdf4f1 : radv,gallium: Add driconf option to reduce advertised VRAM size.
cc431f48f90 : iris: Add missing range_base/range to our nir_load_ubos.
4df0eef1889 : llvmpipe: include gallivm perf flags in shader cache.
fefeaeef060 : aco/isel: Compile all helper functions with static linkage
793dc668eac : aco/isel: Move add_startpgm to aco_instruction_selection.cpp
47de5532836 : aco/isel: Move context initialization code to a dedicated file
1eac0b52e3e : aco/isel: Remove unused definitions
150de6358d2 : aco/isel: Consistently use references for input parameters in emit_load
dab0af06164 : aco/isel: Simplify nested branching code
757de68a436 : aco/isel: Turn the function template emit_load into a proper function
3bd7c3c9dbd : intel/nir: Call validate_ssa_dominance at both ends of the NIR compile
7cedc4128a1 : spirv: Run repair_ssa if there are discard instructions
45bcb108413 : nir: Add a dominance validation pass
6cef8040672 : nir/opt_if: fix opt_if_merge when destination branch has a jump
1ed78bd2479 : nir: Use explicit deref information to provide real UBO ranges.
41b5aafef34 : freedreno/ir3: Apply the max upload limit to initial range setup
f74c3b0404c : freedreno/ir3: Use the new NIR UBO ranges in UBO analysis.
f3b33a5a35e : nir: Add a range_base+range to nir_intrinsic_load_ubo().
3a9356831a9 : nir: Update the comment about nir_lower_uniforms_to_ubo()'s multiplier.
1388c25ada4 : radeonsi: inline trivial PS functions
9fc96152741 : ac,radeonsi: lower 64-bit IO to 32 bits and remove all dead code
e7d606289c6 : radeonsi: remove swizzle == ~0 dead code in si_llvm_load_input_gs
fc44861517c : radeonsi: eliminate unused shader outputs for separate NGG geometry shaders
5c445be39a1 : radeonsi: set outputs_written_before_ps for geometry shaders too
0b6448bbe79 : aco/isel: refactor emit_vop3a_instruction() to handle 2 operand instructions
5b310562575 : aco/isel: refactor code and remove unnecessary v_mov
28df8ffde7c : swr: Use ElemenCount constructor for LLVM 11
6049dc1a9d5 : aco: improve fsign selection
0e9425a1b74 : aco: fix one-off error in Operand(uint16_t)
f4210df2241 : gitlab-ci: Enable unit test report for arm64_a630_traces
88fc3e24d3c : gitlab-ci: Enable unit test reports for lava traces jobs
7e82e252e0f : gitlab-ci: Enable unit test reports for normal runner traces jobs
d24ffd87061 : tracie: Produce JUnit XML results
dd471928c94 : tracie: Make tests independent of environment
171e94fe629 : mesa/st: enable EXT_color_buffer_half_float when formats supported
8447b0f6518 : mesa: add EXT_color_buffer_half_float plumbing
331e5f105eb : mesa: refactor floating point texture fbo completeness check on gles
bb42deee362 : egl/android: HAVE_DRM_GRALLOC path fixes (v2)
9d02d65f464 : android: freedreno/common: add libmesa_git_sha1 static dependency
cc86a13b36e : android: freedreno: Implement pipe screen's get_device/driver_uuid()
9b3491870fc : radeonsi: Work around Wasteland 2 bug.
e4d75c22beb : nir/opt_shrink_vectors: shrink image stores using the format
bd428162b6d : nir/lower_io: Fix the unknown-array-index case in get_deref_align
11bd64bdecd : ci: Remove any existing results directory before running piglit
013a2b123d7 : spirv2nir: Rework argument handling
a5e427fe644 : spirv: Improve the "Entry point not found" error message
2c94a9788e7 : swr: fix build with mingw
c56fbed99b4 : radeonsi: kill point size VS output if it's not used by the rasterizer
234505162c1 : radeonsi: deduplicate setting key.mono.u.vs_export_prim_id
1dd243d4f50 : radeonsi: use shader_info::cs::local_size_variable to clean up some code
757f790ad84 : radeonsi: remove redundant si_shader_info::uses_derivatives
f3f08bca238 : radeonsi: remove redundant si_shader_selector::max_gs_stream
2b4fa688089 : radeonsi: remove redundant GS variables in si_shader_selector
7960668dc95 : radeonsi: remove redundant si_shader_info::writes_memory
83cdffd4358 : radeonsi: rename num_memory_instructions -> num_memory_stores
c8ab5899c1b : radeonsi: reduce type sizes in si_shader_selector
99c4e610840 : radeonsi: remove redundant si_shader_info::uses_kill
8df349a31ec : radeonsi: merge uses_persp_opcode_interp_sample/uses_linear_opcode_interp_sample
7b3e24c2d87 : radeonsi: remove unused si_shader_info::uses_(vertexid|basevertex)
f02cd0e0270 : radeonsi: remove redundant si_shader_info:*(clip|cull)* fields
d15a7d16d6a : radeonsi: remove redundant si_shader_info::const_buffers_declared
0dabcb9e53f : radeonsi: remove redundant si_shader_info::images_declared
c1af2f4bee1 : radeonsi: remove redundant si_shader_info::shader_buffers_declared
cb63e4afc96 : radeonsi: remove info::samplers_declared, image_buffers, msaa_images_declared
cb7bc983ae5 : radeonsi: stop using TGSI_PROPERTY_FS_COLOR0_WRITES_ALL_CBUFS
89cf8789cd1 : radeonsi: stop using TGSI_PROPERTY_CS_LOCAL_SIZE
ebe8238f1b6 : radeonsi: stop using TGSI_PROPERTY_FS_DEPTH_LAYOUT
ce0291df4ac : radeonsi: stop using TGSI_PROPERTY_FS_COORD_PIXEL_CENTER
c597e394d45 : radeonsi: stop using TGSI_PROPERTY_FS_POST_DEPTH_COVERAGE
5aeaf3d7bce : radeonsi: stop using TGSI_PROPERTY_FS_EARLY_DEPTH_STENCIL
ba7b87a8a2d : radeonsi: stop using TGSI_PROPERTY_CS_*
e627528e279 : radeonsi: stop using TGSI_PROPERTY_GS_*
a8e70247925 : radeonsi: stop using TGSI_PROPERTY_TES_VERTEX_ORDER_CW
eeea2f52c7d : radeonsi: stop using TGSI_PROPERTY_TES_SPACING
34b8e60cb86 : radeonsi: stop using TGSI_PROPERTY_TES_POINT_MODE / TES_PRIM_MODE
af59f06918b : radeonsi: stop using TGSI_PROPERTY_TCS_VERTICES_OUT
a37d897d692 : radeonsi: stop using TGSI_PROPERTY_VS_WINDOW_SPACE_POSITION / VS_BLIT_SGPRS_AMD
46bb051bc2a : radeonsi: stop using TGSI_PROPERTY_NEXT_SHADER
4c5f5d238b9 : lima/ppir: Skip instruction merge when having more than one successor
927a395f040 : swr: Fix crashes on non-AVX hardware
e5fb9dca2a1 : amd/common: switch to 3-spaces style
82d2d73e03e : amd/llvm: switch to 3-spaces style
afa1fba198f : vulkan/device_select: don't pick a cpu driver as the default
be31398d224 : android: nv50/ir: Add nv50_ir_prog_info_out serialize and deserialize
d85392952b7 : ci: Run deqp-gles3 and deqp-gles31 on RadeonSI
3d5bed0e883 : radeonsi: fix user fence space when MCBP is enabled
c638301b42b : radeonsi: fix syncobj wait timeout
be2818387dd : android: util: fix missing include path
fb42d73a9d9 : android: amd/registers: switch to new generated register definitions
e8d55e6db36 : ac/llvm: fix b2f for v2f16
d9a77f9ca36 : ac/llvm: add better code for fsign
ca74603b4f6 : ac/llvm: add better code for isign
cecb6d1fbc6 : ac/llvm: remove dead code handling for fmod
44528f51bde : ac/llvm: fix bcsel for v2*16
735c3901e13 : ac/llvm: fix amdgcn.rsq for v2f16
dd8561fda9a : ac/llvm: fix amdgcn.fract for v2f16
ab614abeefb : ac/llvm: fix amdgcn.rcp for v2f16
84500eebd71 : ac/llvm: remove stub prototype for fmed3
f85294207f8 : Revert "ac: generate FMA for inexact instructions for radeonsi"
a407123789e : radeonsi: move nir_shader_compiler_options into si_screen
1476bea7648 : radeonsi: remove redundant no-signed-zero-fp-math LLVM attribute
42420730d1c : egl/x11: Free memory allocated for reply structures on error
4b7f93b4079 : glsl_to_nir: fix crashes with int16 shifts
57fba85da40 : spirv: fix emitting switch cases that directly jump to the merge block
11fbd9806dd : compiler/types: Fix deserializing structs with >= 15 members
50ff8a772ae : freedreno/regs: add 7nm DSI PHY/PLL regs
1d018bc7fde : gallivm: add InstSimplify pass
64b0b7c274c : intel/compiler: fix typo in a comment
95ce619680d : intel/compiler: print dispatch width when shader fails to compile
e5f735a9865 : intel/compiler: move extern C functions out of namespace brw
d4c6e3f196f : intel/compiler: use the same name for nir shaders in brw_compile_* functions
0dda2094066 : intel/compiler: match brw_compile_* declarations with their definitions
a7ece63de99 : nir/algebraic: add 16-bit versions of a few 32-bit patterns
00b28a50b2c : nir/algebraic: trivially enable existing 32-bit patterns for all bit sizes
ac55b1a9a62 : nir: get ffma support from NIR options for nir_lower_flrp
efd439e0d64 : iris: Better determine map_would_stall for Z/S
2c30079628d : iris: Drop a use of the need_resolve boolean
5b82d8ce8bc : iris: Avoid resolving Z/S reads in transfer_map
2982d7c63b6 : iris: Make iris_has_color_unresolved more generic
e7908a95f96 : iris: Fold a condition into no_gpu for consistency
73eb24ab31a : aco: handle unaligned loads on GFX10.3
a083560b09c : nir/load_store_vectorizer: Add unit tests for alignment handling.
c6f72196620 : nir/load_store_vectorizer: Use more imm helpers in the tests.
91a8a07a5f0 : nir/load_store_vectorize: rework alignment calculation
8faf85f6877 : aco: fix byte_align_scalar for 3 dword vectors
663c4d53771 : intel/fs: add hint how to get more info when shader validation fails
ab079260572 : intel: add INTEL_DEBUG=shaders
7acc7ec33b3 : ac/llvm: fix unaligned VS input loads on gfx10.3
aaa492e6c6a : nir: fix const-cast warning on MSVC
0f4d09443eb : meson: drop leftover PTHREAD_SETAFFINITY_IN_NP_HEADER
ebf2576862c : radv,aco: disable opts if VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT
bb80ed88737 : panfrost: Fix gnu-empty-initializer errors.
3cf6325e724 : iris: Fix aux assertion in resource_get_handle
fd2ee49b216 : ci/bare-metal: Use python for handling fastboot booting and parsing
0453a46f668 : ci/bare-metal: Fix capturing of serial output as job artifacts.
24f5f117197 : ci/bare-metal: Log why our run restarts when it does.
785d3cace47 : ci/bare-metal: Include a timestamp in our serial reads.
ff42b7e8041 : ci/bare-metal: Fix detection of "POWER_GOOD not seen in time" fails
b7787ce18df : ci/bare-metal: Use re.search() instead re.match() for our line matching.
93c8777ace8 : amd/common: Fix various non-critical integer overflows
2182bbf84f0 : aco: Fix integer overflows when emitting parallel copies during RA
f18fc34c4d5 : radv: Fix various non-critical integer overflows
a99ae1943d8 : aco: remove omod_success/clamp_success
dc79152be97 : aco: fix mad splitting after applying output modifiers
fdadbdb513e : radv: remove descriptor_indexing fails from expected fails
21fbffc5425 : anv: Set alignments on UBO/SSBO root derefs
c7dec0548af : spirv: Drop the OpenCL type layout code
796d3fe9e0f : clover/nir: Use lower_vars_to_explicit for uniform and global
e1ed5a12c51 : spirv: Stop counting inputs in entry_point_wrapper
8bea5aaa149 : clover: Use args.size() to compute new var locations
9641f483e94 : nir: Allow uniform in nir_lower_vars_to_explicit_types
3719b69dfc4 : nir: Allow var_mem_global in nir_lower_vars_to_explicit_types
3135984ad0b : spirv: Propagate alignments to deref chains via casts
207b462e932 : spirv: Add pointer helper vars to OpCopyMemory
e7fbec0e090 : nir/opt_deref: Remove restrictive alignment information from casts
99bb2a4de66 : nir/opt_deref: Don't remove casts with alignment information
beefd37021e : nir/lower_io: Apply alignments from derefs when available
480329cf8b3 : nir: Add a helper for getting the alignment of a deref
0654a9e8230 : nir: Handle all array stride cases in nir_deref_instr_array_stride
878a8daca6b : nir: Add alignment information to cast derefs
a0b82c24b6d : nir/glsl: Add an explicit_alignment field to glsl_type
ca11b17b7b7 : compiler/types: Make booleans 32-bit for cl_size/align
3be890a3a68 : nir: Expose the packed attribute attached to glsl_type objects
42f97f8ce3a : nir/glsl: Consider block interfaces as structs when it comes to size/align calculation
be68de81abb : glsl: Propagate packed info in get_explicit_type_for_size_align()
d0c2958f882 : spirv: Propagate packed information to glsl_type
938d6ceb830 : spirv: Don't accept CPacked decoration on struct members
bcfeead5f31 : clover: Call nir_lower_mem_constant_vars
9414cbc13c9 : nir: Don't bail too early in lower_mem_constant_vars
a7a0315d7fd : intel/nir: Stop using nir_lower_vars_to_scratch
38a83a30484 : nir/lower_indirect_derefs: Add a threshold
c897cd02785 : intel/compiler: Handle all indirect lowering choices in brw_nir.c
9005c9cae40 : zink: generically handle matrix types
2c5c55e72ac : gallium/util: use uint sampler for stencil-reads
98e866c6695 : radeonsi: optimize out the loop in si_get_ps_input_cntl
6ecb8b68997 : radeonsi: replace TGSI_SEMANTIC with VARYING_SLOT and FRAG_RESULT
a803008c7f1 : radeonsi: replace TGSI_INTERPOLATE with INTERP_MODE
99fe3ef8ba4 : compiler: add INTERP_MODE_COLOR for radeonsi
6925401a387 : radeonsi: remove si_shader_selector::type
23fdb79e92f : radeonsi: change PIPE_SHADER to MESA_SHADER (si_dump_descriptors)
966307983bd : radeonsi: precompute si_*_descriptors_idx in si_shader_selector
cbfc13b27c4 : radeonsi: change PIPE_SHADER to MESA_SHADER (si_shader_dump_disassembly)
62aaa0d0b76 : radeonsi: remove unused si_shader_context::type
5151421ad0f : radeonsi: change PIPE_SHADER to MESA_SHADER (si_get_shader_part)
a90d1df8204 : radeonsi: change PIPE_SHADER to MESA_SHADER (si_compile_llvm)
3c54d73e4b5 : radeonsi: change PIPE_SHADER to MESA_SHADER (debug flags)
b4b323c81ee : radeonsi: change PIPE_SHADER to MESA_SHADER (si_shader_context::type)
b1cb72c4490 : radeonsi: change PIPE_SHADER to MESA_SHADER (si_shader_selector::type)
14391533f81 : radeonsi: simplify handling color interp modes in si_emit_spi_map
562b8c1a479 : radeonsi: don't execute LDS stores for TCS outputs that are never read
08ee72100fe : radeonsi: don't lower indirect IO in GLSL
f4d0565f526 : radeonsi: remove in/out/uniform variables from NIR after lowering IO
81d106d6eca : radeonsi: lower IO intrinsics - complete rewrite of input/output scanning
408fc4e3ac9 : ac/nir: handle all lowered IO intrinsics
44eaee688b5 : radeonsi: clean up code for loading VS inputs
ed9391df3f6 : radeonsi: get color interpolation info from shader_info
0464ee7f9d9 : radeonsi: don't crash if input_usage_mask is 0 for a VS input
bf23ff83e69 : freedreno: fence_server_sync() fixes
aae1e68637f : freedreno: Fix missing rsc->seqno updates
e953f6c0015 : docs: shift 20.2 rc dates by two weeks to match reality
cdb666bc8fb : docs: update calendar and link releases notes for 20.1.7
aca2bda967f : docs: add release notes for 20.1.7
bbaa62e4e15 : iris: Re-emit push constants if we have a varying workgroup size
fe18a0fd45c : intel/nir: Lower load_num_work_groups to 32-bit if needed
5799da47c79 : intel/fs: Use a single untyped surface read for load_num_work_groups
8e8701b43a0 : intel/fs: Don't copy-propagate stride=0 sources into ddx/ddy
95415a54c00 : st/mesa: fix lowered IO - don't call st_nir_assign_vs_in_locations twice
8c43edf9f91 : nir: fix a bug in is_dual_slot in nir_io_add_const_offset_to_base
536727c4651 : iris: Patch constant data pointers into shaders
5ee32428373 : anv: Patch constant data pointers into shaders with using softpin
a06955f4ef6 : nir/builder: Add load/store_global helpers
a5acf3d8c31 : anv: Properly cache brw_stage_prog_data::relocs
91becd84ae2 : intel/fs: Add support for a new load_reloc_const intrinsic
8d8a3815ef6 : intel/eu: Add a mechanism for emitting relocatable constant MOVs
272ab2823d1 : intel/eu: Include brw_compiler.h in brw_eu.h
aff078eb5a7 : anv: Stop storing the shader constant data side-band
90b6745bc80 : intel/fs,vec4: Stuff the constant data from NIR in the end of the program
91348d125d9 : intel/eu: Add some new helpers
bc2c5f9a4b6 : iris: Use gen_disassemble
372774367cf : intel/compiler: Get rid of struct gen_disasm
54ba0daa28b : intel/compiler: Get rid of the global compaction table pointers
191f8a4b9fc : spirv: Deal with glslang not setting NonUniform on constructors.
965b8441fe0 : spirv: Deal with glslang bug not setting the decoration for stores.
61b714a42ee : radv: Avoid deadlock on bo_list.
6b75262941b : radv: Fix threading issue with submission refcounts.
e4dadb545fa : intel/tools: Disassemble WAIT's argument as a destination
329dee14555 : gallium/tgsi_exec: Fix up NumOutputs counting
ed745febe1c : gallium/tgsi_exec: Add missing DFLR opcode support.
9121afe8615 : nir/clone: Add a helper for cloning most instruction types
f25e169897e : nir/opt_vectorize: Add a callback for filtering of vectorizing.
479d9c97eb2 : nir: Add simplistic lowering for bany_equal/ball_inequal.
9ed33383a5b : gallium/ureg: Set the next shader stage from the shader info.
500b0735c0c : gallium/tgsi: Add a helper for initializing ureg from a shader_info.
34b3e1f5121 : gallium/tgsi: Add some missing opcodes to tgsi_ureg.
1ca9f22a8bd : gallium/tgsi: Add support for PRIMITIVEID as a system value.
6e7c006062c : gallivm: Report the unsupported intrinsic instead of just assert(0);
615f1c8990d : ci: Do not create manual test-docs job in post-merge pipelines
ed9ac3d60cf : intel/fs,vec4: remove unused assignments
8e8356e3dcc : intel/compiler: mark debug constant as const
c7a9dc76dce : intel/compiler/test: use TEST_DEBUG env var consistently
289cb6b59ae : intel/perf: don't generate logically dead code
0789f4b6d85 : i965: verify format width in blorp_get_client_bo
5e676ac6717 : iris: verify color component width in convert_fast_clear_color
0685815ea62 : iris: handle os_dupfd_cloexec failure
612ef74190c : freedreno/computerator: Use a render node
87fa645b943 : intel/compiler: Fix pointer arithmetic when reading shader assembly
c601e730b29 : mesa/st: Don't set alpha if ALPHA_TEST is lowered
075e40ea983 : turnip: Implement VK_EXT_host_query_reset
b92be738d56 : turnip: Support pipeline statistics query
170da456efe : turnip: Refactor structs of tu_query
03fbff1efcc : intel/assembler: Add labels support
bc4a127d6e1 : intel/disasm: Label support in shader disassembly for UIP/JIP
6cbd4764cd9 : intel/disasm: brw_label and support functions
afa39d07e46 : intel/disasm: Change visibility of has_uip and has_jip
e94c22429b6 : anv: refresh cached current batch bo after emitting some commands
a1c2bd6ce89 : radeonsi: use radeonsi_clamp_div_by_zero for SPECviewperf13, Road Redemption
b8445520cba : radeonsi,driconf: add clamp_div_by_zero option
32f46a55c82 : ac/llvm: add option to clamp division by zero
f8c0e20152b : radeonsi: enable PIPE_CAP_NO_CLIP_ON_COPY_TEX
d94bec5c49d : mesa/st: introduce PIPE_CAP_NO_CLIP_ON_COPY_TEX
54fed1cf95e : gallium/swr: Fix compilation TCS/TES compilation issues
639605e5ba9 : gallium/swr: Fix compilation with LLVM 12
abbfc5b8db7 : spirv: fix retrieving dest type for OpFragmentMaskFetchAMD
4500e6e460d : vulkan: make VK_TIME_DOMAIN_CLOCK_MONOTONIC_RAW_EXT conditional
7fbeb2623f3 : radv: remove seccomp includes
b30bd6fe5f2 : util/os_misc: os_get_available_system_memory() for OpenBSD
5b1ed09ff02 : anv: use os_get_available_system_memory()
033dcb2978c : util/os_misc: add os_get_available_system_memory()
81b163fb73a : anv: use os_get_total_physical_memory()
0369dd90777 : freedreno/a6xx: Add ARB_depth_clamp and separate clamp support.
5c0d34cee45 : ci: Enable KHR-GL30 CTS testing on freedreno a630.
ef807a52f13 : ci: Use the same VK-GL-CTS tree for GL/GLES as VK.
eb02b311234 : ci: Bump vulkan CTS version to 1.2.3.2, and keep the GL CTS around.
b9df3fef4d5 : panfrost: Drop PIPE_CAP_MAX_COMBINED_HW_ATOMIC_COUNTER/BUFFERS
d7b6d2e792e : panfrost: add support for atomics
8e221f58a66 : panfrost: add atomic ops infrastructure
703b03bd452 : panfrost: add support for src[3] in LOAD_STORE ops
f61190024e3 : panfrost: introduce LDST_ATOMIC property
16664fc6418 : panfrost: add LDST_ADDRESS property to atomic ops
8e8805b212d : panfrost: add atomic_cmpxchg opcode
11012611d7f : panfrost: fix undefined value access on mir_set_intr_mask()
526f3566332 : clover: Use 64-bit offsets for shader_in on 64-bit GPUs
c93ade93fb9 : nir/lower_explicit_io: Assert that compute address sizes match derefs
6678f1e81cc : spirv: Drop the constant_as_global as option
26a4c8f375e : clover/nir: Use nir_var_mem_constant for __constant memory
dfa63f26561 : llvmpipe: Add support for load_global_constant
4087b5343d8 : nouveau/nir: Implement load_global_constant
ff2f44d8658 : intel/fs: Implement nir_intrinsic_load_global_constant
1bdf8506384 : spirv: Use nir_var_mem_constant for UniformConstant data in CL
bb8d8ba9c7f : nir: Allow opt_large_constants to be run with constant_data_size > 0
4360a8a2b3f : nir/lower_io: Add support for nir_var_mem_constant
ef142c68e11 : nir/lower_io: Add a build_addr_for_var helper
965c2688657 : nir/lower_io: Use the variable mode for load_scratch_base_ptr checks
ff124e3fe3e : nir: Add a load_global_constant intrinsic
e4f07f8bdc6 : nir: Add a new nir_var_mem_constant variable mode
b9927c8c8d0 : nir/serialize: fix serialization of system values
5c45eaf9b35 : clover/spirv: fix vec3 alignment
6e52c6dfcc9 : nvc0/cl: hande 64 bit pointers in nvc0_set_global_handle
5eacaa95a78 : spirv: fix 64 bit atomic inc and dec
1c9efcd7a6f : nvc0/ir: fix load propagation for sub 4 byte addressing
036f1c29fc7 : clover/llvm: undefine __IMAGE_SUPPORT__ for devices without image support
7dc39838edb : clover/nir: use offset for temp memory
d7b65cf7d3d : nv50/ir: fix cas lowering for 64 bit
d421af3a993 : clover/nir: Lower function_temp to scratch.
8e259dad4cf : egl/x11: simplify dri2_initialize_x11()
bd385c424bd : egl/wayland: simplify dri2_initialize_wayland()
f7e0cdcf1a5 : egl/surfaceless: simplify dri2_initialize_surfaceless()
83b5c1abc6c : egl/android: simplify dri2_initialize_android()
cccb497d3c3 : intel/fs: Fix MOV_INDIRECT and BROADCAST of Q types on Gen11+
70cbddc4a79 : nir: use enum operator helper for nir_variable_mode and nir_metadata
76a1fb3b42c : util: add helpers to define bitwise operators on enums for C++
24dfd798d62 : nir: use nir_var_all to get rid of casting
15da9836538 : nir: Improve the comment on num_inputs and friends
4d18e71fea9 : nir: Rename num_shared to shared_size
471f260ef36 : spirv: Delete some dead workgroup variable handling code
1459cce7ec7 : spirv: add some tests for volatile/available/visible
fb6b243c113 : spirv: Support big-endian strings
a8d8fbb9ce1 : spirv: implement SpvMemoryAccessVolatileMask
f81e1d2824e : spirv: implement Volatile image operand
2ba3ffa76c6 : spirv: implement Volatile memory semantic
23bfba8663c : spirv: implement MakePointerAvailable/MakePointerVisible for OpCopyMemory
e01d1a9f16d : spirv: add vtn_emit_make_{visible,available}_barrier helpers
b85c38a86f9 : spirv: make OpLoad/OpStore visibility/availablity barriers acquire/release
5b92392c483 : spirv: fix Uniform and Output MemoryAccessMakePointer{Visible,Available}
857b9c50276 : spirv: Add a vtn_get_mem_operands() helper
959539fbbd1 : intel/isl: Drop unnecessary check on 16bpp depth format
829699ba632 : anv: implement shareable timeline semaphores
a965ffad21d : anv: add new gem/drm helpers
a0c07e41e52 : include/drm-uapi: bump headers
a6291b1b117 : freedreno/ir3: rework setup_{input,output} to make struct varyings work
c694af40bf3 : freedreno/ir3: improve handling of aliased inputs
acb6163d5e6 : freedreno/ir3: remove indirect input load
00973542ffe : radv: Allow triggering thread traces by file.
0d862da1706 : radv: Centralize enabling thread trace.
b7a6333ee40 : amd/registers: switch to new generated register definitions
e492a3195c2 : amd/registers: add non-gfx10 register files generated from kernel headers
48a7a24a69f : amd/registers: add a script that generates json from kernel headers
b2f23afe668 : amd/registers: sort registers by offset in json
843b4e631f0 : amd/registers: expose the canonicalize.py program as a function
ec5e918ef49 : vulkan/wsi/x11: wait for acquirable images in FIFO mode
d0bc1ad3776 : vulkan/wsi/x11: add sent image counter
68957a82562 : aco: Add README which explains about what ACO is and how it works.
b4d4c548eb5 : aco: Fixup markdown formatting of the README-ISA.
086fafc4e00 : aco: Move README to README-ISA
bc123c396a9 : nir/algebraic: mark some optimizations with fsat(NaN) as inexact
a6c4db9798b : ci: Restrict "success" job to pipelines for MRs
d383133ce1d : docs: Stop claiming to implement OpenVG
0308e639cf7 : ci: Don't exclude "success" job from mesa/mesa pipelines for MRs
f13f32f83f3 : ci: Create test-docs job in mesa/mesa pipelines for MRs
52cac068621 : gallivm: fix build on LLVM 12 due to LLVMAddConstantPropagationPass removal
8b1ab78985b : radv: dump GPU info into the hang report
aa675cdc91f : radv: improve reporting faulty pipelines when a GPU hang is detected
dd1f035f6e7 : radv: force RADV_DEBUG=syncshaders when RADV_TRACE_FILE is used
004119d5b7d : vulkan: Fix memory leaks.
7036b3872f7 : ANDROID: Bring back gbm target, renamed to gbm_mesa
50e14c3d258 : radv/winsys: Fix memory leak.
b778e7bd6c1 : nir/vtn: Convert constant samplers to variables with data
397730edd5b : nir/vtn: Add intrinsics for CL image format/order queries
5ce6821900f : nir/vtn: ImageSizeLod op can be applied to images
701cb9d60c0 : nir/vtn: Handle integer sampling coordinates
a196f05fc22 : nir/vtn: Use return type rather than image type for tex ops
de36b5b805b : nir/vtn: Add support for kernel images to SPIRV-to-NIR.
ce6f66242ad : nir/vtn: Add type constant to image intrinsics
865a2ad0866 : clover/nir/spirv: Use uniform rather than shader_in for kernel inputs
41d0a81c2a3 : pan/mdg: Fix perspective combination
c8ac01af33a : pan/mdg: Fix discard encoding
9efdbb2af47 : anv: fix robust buffer access
73d2c6cdce8 : nir: Switch the indexing of block->live_in/out arrays.
5d2b2b59c45 : nir: Invalidate live SSA def information when making new SSA defs.
d3b652f13d8 : ci: Switch to using gold as the linker.
8c4fb19f096 : pipe-loader: Use real galliumvl if radeonsi is being linked.
221aa00eeb3 : turnip: Make sure we include the build id.
2d1c6070052 : ci: Make a missing device name correctly bail out of deqp-runner.sh.
ee288f293b3 : nir: add shared/global atomics to nir_get_io_offset_src()
e281ee04dfe : nir: Look up the shader when printing a single instruction.
a3a8322dcd7 : nir: Fix printing of individual instructions with io semantics.
4c050f222fd : panfrost: enable DrawTransformFeedback*
e8b3bc1d553 : intel/nir: Lower things with > 4 components in lower_mem_access_bit_sizes
55ae7045135 : intel/fs: Add support for vec8 and vec16 ops
b6a013ccab0 : anv: VK_INTEL_performance_query interaction with VK_EXT_private_data
5d52c26e78b : vulkan: Don't pointlessly depend on libxcb-dri2
8239fe5d742 : zink: add note about buffer<->image copy functions not handling multisample
d84a75466c9 : zink: use u_transfer_helper to split/merge interleaved depth/stencil formats
7059708dcdb : broadcom/qpu_instr: wait is not a read or write vpm instruction
efd29d429ea : docs/features: Add missing Panfrost extensions
8ff6e7c7399 : panfrost: Set PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS
7dab5749c89 : pan/mdg: Implement texture gathers
661123bb19d : pan/mdg: Add disassembly for shadow gathers
f6e19dd3f45 : pan/mdg: Refactor texture op/mode handling
80ebf110aed : pan/mdg: Implement nir_intrinsic_load_sample_mask_in
41184f89eb9 : pan/mdg: Bounds check swizzle writing globals
2486fe6761d : pan/mdg: Scalarize 64-bit
3e2cb21e53c : pan/mdg: Implement i/umul_high
fd41dece39c : panfrost: Emit texture/sampler points for compute
55765f80b9c : util/u_thread: include pthread_np.h if found
c66c5b38e0a : util: futex fixes for OpenBSD
0398caa97fa : meson: conditionally include -ldl in gbm pkg-config file
c97af23b13c : meson: don't build with USE_ELF_TLS on OpenBSD
9ac16864227 : meson: don't advertise TLS support if glx wasn't build with it
f9a7e6e854d : meson: build with _ISOC11_SOURCE on OpenBSD
6e9c0661f85 : util/anon_file: add OpenBSD shm_mkstemp() path
7eab6845e9d : util: unbreak endian detection on OpenBSD
8301a43f272 : radv: dump shader stats with VK_KHR_pipeline_executable_properties
35a42ff9c59 : vallium: disable VK_KHR_shader_float16_int8.
8f6eb35e097 : gallivm/nir: add some f16 support
b31e8460a6b : gallivm/nir: allow 64-bit arit ops
dc6313b0982 : llvmpipe/fs: multisample depth/stencil bad ir generated
6d60cd44f3f : llvmpipe: add array/3d clearing support
2d6385715da : llvmpipe: blend has effects even if no colorbuffers.
727bb217be6 : gallivm: use common code to select texel type
6596957641f : gallivm/nir: add subpass sampler type support
21324c40366 : gallivm/nir: lower frexp/ldexp
d7aed02bcca : gallivm/nir: fix const compact
96a5ced65f6 : gallivm/nir: add quantize to f16 support
1d4a560ba26 : gallivm/nir: add indirect swizzle output loading support
5177ffed656 : gallivm/nir: lower tg4 offsets.
87a638dc1f6 : gallium/nir/tgsi: fix nir->tgsi info conversion for samplers/image
668e4c23565 : vallium: limit buffer allocations to gallium max.
857008850f3 : vallium: handle 3D image views properly.
99330e50c9e : llvmpipe: add reference counting to fragment shaders.
ac6b8e42ce2 : nir: Take a variable remap parameter in nir_inline_function_impl
b6f31898a24 : nir: Use a switch in nir_inline_function_impl
b7db9ee320f : intel/nir: Clean up lower_alpha_to_coverage a bit
b6fdb1405ee : intel/nir: Rewrite the guts of lower_alpha_to_coverage
72dc06e07e3 : intel/nir: Pass the nir_builder by reference in lower_alpha_to_coverage
373e25e6b53 : ci: Add a release build with -Werror enabled.
60fb460f9d7 : virgl: Fix unused var warnings in release build from assertions.
c24f792c8b4 : lima: Fix uninitialized var warning from using assert() as unreachable().
f6456d74ed0 : lima: Fix unused var/function warnings in release build from assertions.
65f484198a3 : etnaviv: Fix unused var warning in release build from assertions.
ab6a09f25b9 : zink: Fix unused var warnings in release build from assertions.
ca73c3bc596 : nv50: Fix uninitialized var warnings from using assert() as unreachable().
689e36ebfe4 : vc4: Fix unused var warnings in release builds from assertions.
26471264bf7 : nvc0: Fix compiler warning about unused var that gets asserted.
b9972fb6f58 : gallium/tests: Fix compiler warning about unused vars in trivial tests.
4c24c8239a5 : panfrost: Fix remaining release-build warnings.
ecab580d48f : panfrost: Fix OOB array access compiler warning.
ccb5e0b02b2 : drm-shim: Fix unused variable warnings from asserts in release build.
8d1d0c126fd : freedreno/a6xx: move ubwc clear to blitter
8d9ab0a33bb : freedreno/a5xx+a6xx: use sysmem path for nondraw batches
21b90708a4c : freedreno/batch: replace lrz_clear with prologue
28079970f2c : freedreno/batch: split out helper for rb alloc
40eceb55fc0 : ANDROID: Remove conflicting gbm target
9522eb7be14 : panfrost: Store transient BOs in a dynamic array
d87ab72ce95 : panfrost: Avoid accessing pan_pool fields directly
4047c691bff : panfrost: Rename panfrost_create_pool() into panfrost_pool_init()
b8f2d71c404 : CI: Disable Windows again
7fbded8b582 : pan/decode: Drop prefix braces
eb261a80187 : panfrost: Remove mali_vertex_tiler_postfix
760289174b8 : pan/decode: Use unpack for vertex_tiler_postfix_pre
2425bac8fee : pan/decode: Use generation for vertex_tiler_postfix
80049069265 : pan/decode: Fix awkward syntax
c088a3b5542 : pan/decode: Print shader-db even for compute
68552287261 : pan/decode: Drop mali_vertex_tiler_postfix arg
38ae0885654 : pan/decode: Drop scratchpad size dump
c92be29a477 : panfrost: Use nir_builder_init_simple_shader for blits
4467e792c51 : panfrost: Inline bifrost_tiler_only
0c1f44bab74 : panfrost: Drop bifrost_payload_fused
02e768e6a96 : panfrost: XMLify invocations
0225ed4d72c : panfrost: Add invocation XML
b60d567edd6 : panfrost: XMLify primitive information
3bae493d1a1 : panfrost: Drop point sprite from shader key
b17b6cca362 : panfrost: Cleanup point sprite linking
7d328e7ba9b : panfrost: Simplify ZSA bind
90cc8156289 : panfrost: Use pack for draw descriptor
33895ac2c8a : panfrost: Use draw pack for compute jobs
e5c77cbead9 : panfrost: Detangle postfix from varying emits
3a4d9305715 : panfrost: Inline panfrost_vt_set_draw_info
3f61da79c36 : panfrost: Inline panfrost_vt_init
136fd5cd2e8 : panfrost: Don't call panfrost_vt_init for compute
1513392e776 : panfrost: Avoid postfix dep for vertex_data
8b5f9fc08af : panfrost: Remove postfix parameter from UBO upload
1357eec801c : panfrost: Inline vt_update_{rasterizer, occlusion}
b7169367fd6 : panfrost: Separate postfix from emits
59b6e3c98ce : panfrost: Use draw pack for blit
d6a5df0db0b : panfrost: Add XML for mali_vertex_tiler_postfix
e213a864e57 : panfrost: Add padded type for instance fields
45c59db7325 : panfrost: Drop blend indirection
87e35102ddf : panfrost: Emit explicit REPLACE for disabled colour writeout
75a274de061 : panfrost: Add opaque midgard_blend XML
0e13f803afa : CI: Re-enable VS2019 build
a2808108e80 : CI: Windows: Use separate config file for Docker
f4c1c213060 : egl: simplify eglSwapInterval() fallback logic
1d3fb7a7a7d : egl: inline eglSwapInterval() fallback
957bbc6ad90 : anv: simplify push constant emissions
7953402e575 : anv: move push constant allocation tracking into gfx pipeline state
8076c7596db : aco: fix wrong source position for constant with nir_op_cube_face_coord
f4d861696df : radv: set BIG_PAGE to improve performance on GFX10.3
d6bc0f26c91 : radv: emit {CB,DB}_RMI_L2_CACHE_CONTROL at framebuffer time
31f75aaeefe : nir/lower_discard_to_demote: Use nir_shader_instructions_pass().
265dcb38367 : nir/nir_lower_wrmasks: Use the nir_lower_instructions_pass() helper.
c5e64c041fd : nir/lower_io_to_scalar: Convert to use nir_shader_instructions_pass().
dfb84653417 : nir/opt_undef: Convert to use nir_shader_instructions_pass().
e5d4bbd8406 : nir/lower_vec_to_movs: Convert to use nir_shader_instructions_pass().
a62098fff20 : nir: Add a helper for general instruction-modifying passes.
a82f664d0a4 : nir/opt_copy_prop_vars: Quiet valgrind warning about overlapping memcpy.
98222db0da5 : egl: document which driver hooks are only required by extensions
cf663d0d11c : egl: move extension driver functions after core functions
12c941808ff : docs/egl: correct/update DRI2 mention with the shiny new DRI3
ab2e59750f2 : docs/egl: add some more documentation
7897c315d4f : docs/egl: add haiku driver
c84d3049b01 : docs/egl: complete list of dri2 platforms
3909e9d1ac9 : docs/egl: move section around
3704b0250c9 : docs/egl: fix typo
608c87afddd : nir/vtn: SPIR-V bit count opcodes (core and extension) dest size mismatches nir
a54695ddcb2 : nir: Add bit_count to lower_int64 pass
d91f85f16e0 : nir: Remove 32bit restriction for uadd_carry optimization
9232887c699 : nir: Implement mul_high lowering for bit sizes other than 32
ea715741b5b : nir_lower_bit_size: Support lowering ops with differing source/dest sizes
0d595f72b2c : nir: Relax opt_if logic to prevent re-merging 64bit phis for loop headers
43d22c8f201 : nir: Add a lowering pass to split 64bit phis
6b1a56b908e : iris: Drop stale syncobj references in fence_server_sync
e98c7a66347 : iris: Reorder the loops in iris_fence_await() for clarity.
45793c00d29 : ci: Fix up rules for post-merge / main project branch pipelines
502b9daa7aa : aco: add ACO_DEBUG=novn,noopt,nosched for debugging purposes
4d40a719b07 : radv: Fix 3d blits.
003ea78b774 : st/mesa: remove useless code for lowered IO in st_nir_assign_vs_in_locations
86840619758 : ci: Test the KHR-GL* CTS cases with softpipe.
d2cf6a8399e : aco: sink get_alu_src() in bfe lowering
14d748eb28e : aco: fix sgpr ubfe/ibfe if the offset is too large
454bc595d18 : aco: remove 64-bit SGPR ubfe/ibfe
eb3c16e1f8f : aco/tests: add tests for long jumps
192b9f43039 : aco: shorten disassembly for repeated instructions
ae6330d955e : aco/tests: add test for GFX10 0x3f bug
fe2dc41258b : aco: create long jumps
156fd58cdac : aco: reserve 2 sgprs for each branch
e8ac14527a2 : aco: keep loop live-through variables spilled
75d6c30572c : aco: fix spills_entry heuristic for branch blocks in init_live_in_vars()
fc9f502a5bd : aco: fix regclass checks when fixing to vcc/exec with Builder
a537c9e73f8 : aco: don't fix break condition for break+discard to exec
1a5444b9001 : aco: don't consider the first partial spill if it's the wrong type
8f6a900d5e5 : aco: consider branch definitions in spiller
cacb388b3b7 : radv: print a warning when RADV_TRAP_HANDLER is used
60975ebe58d : etnaviv: Add lock around pending_ctx
da660c90bf9 : etnaviv: Remove etna_resource_get_status()
785e2707b0d : etnaviv: Fix disabling early-z rejection on GC7000L (HALTI5)
0d8ae4ac150 : radv: fix setting EXCP_EN for different shader stages
05a03499499 : v3d: set instance id to 0 at start of tile
2e8b6f64dec : v3d/packet: fix typo on Set InstanceID/PrimitiveID packet
15bdbf34c4f : freedreno/a5xx: Don't set the VARYING flag for fragcoord-only programs.
36bd3e98683 : gallium/dri2: Report correct YUYV and UYVY plane count
7323062a872 : ci: Mark the rest of compswap as flaky on freedreno.
27e6117ee9f : nir: Report progress properly in nir_lower_bool_to_*
39d00722b22 : freedreno/a6xx: fix hang with large render target
0f3c12c0ab0 : freedreno: add env var to override tiles-per-pipe
688ca541e7b : freedreno: add env var to override GMEM size
758fdb9f331 : freedreno/gmemtool: add tile_alignw/h and a650
a61890883dd : radeonsi: fix tess levels coming as scalar arrays from SPIR-V
e512f2cef92 : mesa: add NV_copy_depth_to_color support for nir
da9d721323d : nvc0: Add shader disk caching
82dd683a3ce : nv50/ir: Add nv50_ir_prog_info serialize
3e99af66b4e : nv50/ir: Add prog_info_out print
f20a210dc85 : nv50/ir: Add nv50_ir_prog_info_out serialize and deserialize
5ecc06ef20e : nv50/ir: Use a bit field in info_out structure
f2924994bd3 : nv50/ir: add nv50_ir_prog_info_out
fa8e6282407 : nv50/ir: remove symbol table support for compute shaders
83139aca59a : radv: Update CTS version.
4e30191c9d3 : radv: Remove conformance warnings with ACO.
2a9ffc24cc7 : nir: Move new edgeflag assert into the io_lowered case
2fcfcca842a : nir: Copy semantics to nir_intrinsic_load_fs_input_interp_deltas
3cda33360e7 : panfrost: Drop mali_shader_meta
3d7ce134167 : pan/decode: Use unpacks for state descriptor
1b377c2e591 : panfrost: Use pack for fragment shaders
c86b51a7fa7 : panfrost: Use opaque pack for vertex shaders
100b15cdc82 : panfrost: Add optional opaque packs to GenXML
a7b2317d0a0 : panfrost: Use pack for Bifrost test state
5b3b2a66979 : panfrost: Use pack for blit shaders
a36ac2b9b05 : panfrost: Inherit default values from structs
754d5438295 : panfrost: XMLify the rest of shader_meta
80f1d611c5d : panfrost: Use preuploaded shader descriptors
1e4c49e0b5d : panfrost: Upload shader descriptors at CSO create
8c14482cdf1 : panfrost: Allocate a state uploader
da677a438f2 : panfrost: Ensure shader-db state is zero-initialized
e0a6af9d7b7 : panfrost: Simplify shaderless packing
55d9c25b5a9 : panfrost: Prepack fragment properties/preload
a29fb64c168 : panfrost: Pack vertex properties when compiling
5393d734a85 : panfrost: Derive UBO count from shader_info
661b46958d7 : panfrost: XMLify beginning of shader descriptor
3bb61e21f8b : panfrost: Derive texture/sampler_count from shader
d353b15beec : panfrost: Quiet pandecode error
a0857e9d9eb : panfrost: Support SHADERLESS mode everywhere
c9858fb941c : panfrost: Identify additional SFBD flags
7a95ed2ecf4 : panfrost: XMLify Bifrost preload
1574866233a : panfrost: Group SFBD code tighter
518537d1c8c : panfrost: Drop redundant NULL check
acf77cbb398 : panfrost: XMLify bifrost1
1b7d4f1940c : panfrost: Remove midgard1 bitfield
0268e8481e3 : panfrost: Simplify bind_blend_state
96a91530368 : panfrost: Fold work_count packing for blend shaders
41aad9aff9d : panfrost: Use pack for shaderless
19ded1e1212 : panfrost: Use packs for fragment properties
d4754128596 : panfrost: Pack compute Midgard properties
87c59514e95 : panfrost: XMLify Midgard properties
68503f3dd5c : panfrost: Group SFBD state together
58ae50f1b18 : panfrost: Clean up blend shader errata handling
8073e27d02b : panfrost: Rename shader emit functions
9a2df304edb : panfrost: Specialize compute vs frag shader init
9f83217bc8c : panfrost: Bake the initial tag into the shader pointer
606f05b9ab3 : panfrost: Clamp shader->uniform_count
e45142113c8 : panfrost: Size UBO#0 accurately
e5689a57135 : panfrost: Combine frag_shader_meta_init functions
bf6d5487870 : panfrost: XMLify blend equation
6beac11868c : panfrost: Honour load_dest/opaque flags
919818a8a00 : panfrost: Simplify make_fixed_blend_mode prototype
94c9f87df1a : panfrost: XMLify blend flags
bbec4ff9464 : panfrost: Separate shader/blend descriptor emits
cfef6de429d : panfrost: Hoist blend finalize calls
6fd62215fab : panfrost: Decode nested structs correctly
aac5a559cc2 : pan/decode: Drop legacy 32-bit job support
bc6d6fd0ed5 : scons: bump c++ standard to 14 to match meson
0fd33207b77 : radv: allocate the TMA BO into 32-bit addr space
d243d21ffc9 : radv: align the TMA BO size to 256
2dbb87282fe : gitlab-ci: Test the traces from bgfx
88b935bb0c0 : mesa: fix formatting of messages printed using _mesa_log
fd10cb8cfcc : anv: fix transform feedback surface size
5e4d69ec786 : st/mesa: Fix EGLImageTargetTexture2D for GL_TEXTURE_2D
855afe01449 : meson: Fix lmsensors warning message.
c6861b9f755 : freedreno: Drop UNIFORM_BUFFER_OFFSET_ALIGNMENT to 32
a79dad950b1 : nir,amd: remove trinary_minmax opcodes
1fa43a4a8ec : freedreno: handle case of shadowing current render target
743ad7bf6b8 : freedreno: add debug helper to dump buffers
6f9bb6c26ac : freedreno/a6xx: refactor debug logging
440aab95c3d : gallium/tgsi: add helper tgsi_get_interp_mode
2519472845a : st/mesa: handle lowered IO in st_nir_assign_vs_in_locations
2424485fb43 : st/mesa: don't generate NIR for ARB_vp/fp if NIR is not preferred
493fdcf4464 : st/mesa: don't pass NIR to draw module if IO is lowered
484a60d5474 : nir: generate lowered IO in nir_lower_passthrough_edgeflags
7980f3e519f : nir: add interpolation qualifiers for color sysvals into shader_info
4d36dceeabc : nir: add shader_info::io_lowered
844167d1009 : nir: properly identify texcoords for lowered IO in nir_lower_drawpixels
2b1ef5df4ea : nir: print IO semantics (v2)
01ab308edc7 : nir: update IO semantics in nir_io_add_const_offset_to_base
17af07024df : nir: gather all IO info from IO intrinsics
502abfce7f5 : nir: save IO semantics in lowered IO intrinsics
ec1fa1d51ff : intel/perf: fix raw query kernel metric selection
f1da3bb3d5e : intel/perf: store query symbol name
a9019d14aed : nir/load_store_vectorizer: Clean up unit test swizzle assertions.
2b252409937 : freedreno/ir3: Replace our custom vec4 UBO intrinsic with the shared lowering.
73616598bd2 : nir: Add a lowering pass for backends wanting load_ubo with vec4 offsets.
d84a16e4817 : nir: Add nir_[iu]shr_imm and nir_udiv_imm helpers and use them.
e78b887f767 : nir: Make the nir_builder *_imm helpers consistently handle bit size.
f820dde201f : aco: Fix convert_to_SDWA when instruction has 3 operands.
0d194a70c64 : aco: Fix unused variable warning by adding ASSERTED.
089bc22de53 : r300: Use util_blend_factor_uses_dest
7a776f43d20 : si: Use util_blend_factor_uses_dest
e0554634592 : gallium: Add util_blend_uses_dest helper
e05930511b7 : gallium: Add util_blend_factor_uses_dest helper
48a910d1f93 : radv: use the trap handler to detect faulty shaders/instructions
8e97a61cfbb : radv: enable the trap handler and configure the shader exceptions
af3230e39e9 : radv: add initial trap handler support with RADV_TRAP_HANDLER=1
8fd2f5c16d9 : radv: add a small interface for creating the trap handler shader
a0814a873d5 : aco: skip unnecessary compiler pass for the trap handler program
9c46e6fca32 : aco: add a helper for building a trap handler shader
a6146aa5980 : aco: validate that SMEM operands can use fixed registers
baa9268eb68 : aco: add TBA/TMA/TTMP0-11 physical registers definitions
7e493e510b7 : amd/registers: add some SQ_WAVE_* register definitions
3aa71a61dde : amd/registers: add missing TBA registers on GFX6-GFX8
5e841e8b4fd : nir: add iabs-lowering code
9e5e3be4122 : egl: drop invalid shebang
32dc71b23ac : clover: Call clang with -O0 for the SPIR-V path
e3e45e2456d : clover/spirv: Don't call llvm::regularizeLlvmForSpirv
c84e2784eb2 : intel/nir: Allow splitting a single load into up to 32 loads
febe7622468 : intel/fs: Fix an assert in load_scratch
63dd1e980c6 : iris: Always re-upload sysvals when we have kernel inputs
b4b39b802bd : iris: Normalize all compute shaders to MESA_SHADER_COMPUTE
d0a8ad77e99 : iris: ref/unref the GLSL type singleton in screen_create/destroy
b9678aa17d3 : iris: Stop advertising clover-only caps
6ec286935ae : iris: Stop advertising PIPE_SHADER_IR_NIR_SERIALIZED
4fd2a452675 : clover/nir: add support for global invocation id offsets
47e52d84ea3 : nir: fix nir_variable_create for kernels
368e9a0b545 : spirv: Use new global invocation offset system value
d3faac7a155 : nir: Add options to nir_lower_compute_system_values to control compute ID base lowering
2e1df6a17ff : nir: Move compute system value lowering to a separate pass
58074143f54 : compiler/nir: make lowering global-id to local-id optional
41e4eb9948d : nir: Add new system values and intrinsics for dealing with CL work offsets
6b1515cb849 : nir: Populate some places where existing system values were missing
2da1178bf3e : ci/bare-metal: Try rebooting chezas again if they get stuck during tftp.
c27075e9e15 : ci/bare-metal: Retry booting chezas instead of failing when !POWER_GOOD
c63648121e1 : ci/bare-metal: Convert the main cros-servo boot code to python
b4374080d7a : ci/bare-metal: Use a new serial buffer tool.
ca7d66e847d : virgl: update protocol headers
42e29feb8bd : virgl: move protocol headers to a common place
a4c708dd24e : util/ralloc: fix ralloc alignment.
fd7e1ed86d8 : svga: fix draw elements with 8-bits indices
f41848a9df3 : winsys/svga: fix display corruption after surface_init
090239ea6b7 : st/mesa: increase size of gl_register_file bitfields
e5899c1e881 : nir: rename nir_op_fne to nir_op_fneu
85b7403909d : bifrost: use nir_intrinsic_has_type
2133e642037 : aco: use nir_intrinsic_has_access
7530f66c162 : nir: add and use nir_intrinsic_has_ helpers
9c1e0d86a81 : aco: fix non-rtz pack_half_2x16
e802bff69ee : glsl: Eliminate out-of-bounds triop_vector_insert
5922d57a184 : glsl: Eliminate assigments to out-of-bounds elements of vector
e93979ba599 : ir_constant: Return zero on out-of-bounds vector accesses
b243a74768e : anv: support fd==-1 in ImportSemaphoreFdKHR
f1531517303 : aco: add ACO_DEBUG=force-waitcnt to emit wait-states
258ef4d4a4b : wgl: Switch to Win10 version defines to enable usage of Win10 WGL callbacks
f811ddf5d1f : radv: ignore BB labels when splitting the disassembly string
89b56f19412 : anv: take depth in to account in anv_GetImageSubresourceLayout
3dd1a81aa0e : iris: Add missing newline to debug log message
fb525ada148 : ci/freedreno: List more common flakes reported recently.
c19b7fc0240 : ci/freedreno: Move our skips lists over to being known-flakes lists.
30da82c74c2 : ci/deqp-runner: Add a post-deqp-run filter list for known flakes.
4bb59fcee9c : ci/deqp-runner: Drop unused "count" variable
32fd2ee0236 : ci/deqp-runner: Drop stale comment from deqp-runner.sh.
42d7bbfc228 : nir: Use 'unsigned' instead of enum types in nir_variable::data
1ccd681109e : nir: Add an LOD parameter to image_*_size
a1049025905 : broadcom/compiler: Enable PER_QUAD for UBO and SSBO loads.
c3258f927c4 : broadcom/compiler: Add a constant folding pass after nir_lower_io
bd87cdad181 : broadcom/compiler: support nir_intrinsic_load_sample_id
adda97c98bf : clover/spirv: pass list of supported extensions to the translator
a624faeef98 : clover/nir: Register callback for translation messages (v2)
2402466a08c : clover/llvm: Use the highest supported SPIR-V version (v4)
6ed87594b12 : meson: Raise minimum version for SPIR-V OpenCL deps (v4)
ec6bad140b7 : clover/spirv: Print linked SPIR-V module if asked
a9ca73730e4 : clover/spirv: Remove unused tuple header
e9ddb9b2ae8 : clover/spirv: rework handling of spirv extensions
1cfbc5cff59 : panfrost: Fix alignment on Bifrost
b708a1acb84 : tu: Enable VK_KHR_multiview
c0c7dbd1034 : tu: Implement multiview pipeline state
c884afc6f71 : tu: Add multiview lowering pass
7b53ac1c1f4 : tu: Implement multiview query interactions
ff5f4609804 : tu: Improve timestamp queries
6c446fe650b : tu: Implement multiview clear/resolve interactions
99a87e5e0ec : tu: Parse multiview render pass info
f01a0dc27ad : tu: Translate VkRenderPassMultiviewCreateInfo to VkRenderPassCreateInfo2
5ef960e93cd : ir3: Add support for gl_ViewIndex in VS & FS
4b163ff1eb3 : freedreno/a6xx: Add multiview registers
6a8aaf7c007 : freedreno/a6xx: disable LRZ when color channels are masked
4de027d6bf0 : freedreno/cffdump: add arg to filter by process name
b440c28b78f : nir: Shrink store intrinsic num_components to the size used by the writemask.
5f26c21e624 : nir: Expand opt_undef to handle undef channels in a store intrinsic.
a29b7b6ff5c : nir/opt_undef: Handle a couple more normal store intrinsics.
b3c822a0a86 : radv: Move nir_opt_shrink_vectors() into the opt loop.
94f4ecba8dd : panfrost: Reduce attribute buffer allocations
9a6934d67f4 : panfrost: Don't reserve for NPOT w/o instancing
09ea7c09cc4 : panfrost: Don't overallocate attributes
3df90c7c27e : panfrost: Fix attribute buffer underallocation
373a204bdd7 : panfrost: Pass alignments explicitly
1cb47f8eea0 : panfrost: Free batch->dependencies
680fb05f99d : panfrost: Use memctx for sysvals
8dd38e5a3e6 : pan/mdg: Free previous liveness
62637a913ab : panfrost: Free hash_to_temp map
da6d0e3facf : panfrost: Free NIR of blit shaders
9146f596ed1 : panfrost: Free cloned NIR shader
ba4fc67812c : panfrost: Fix blend leak for render targets 5-8
4ff4b04b50d : panfrost: Keep finalized blend state constant
93200ce4c6f : panfrost: Drop depth-only case in blend finalize
8249e2b9a23 : panfrost: Explicitly handle nr_cbufs=0 case
dc7fbe114ba : panfrost: Drop implicit blend pooling
d8deb1eb6a2 : panfrost: Share tiler_heap across batches/contexts
01d12c353e2 : pan/decode: Don't try to dereference heap mapping
b41692caf42 : panfrost: Avoid minimum stack allocations
17c617cdb7f : panfrost: Introduce invisible pool
40c0d7a13df : panfrost: Pre-allocate memory for pool
3fed1c75ef4 : iris: Fix headerless sampler messages in compute shaders with preemption
58817bda8bc : aco: fix file leak in ra_fail()
74ac8f3f648 : nir/opt_large_constants: Fix a type/deref_type typo
e5bac3c669c : gitlab: ask for more detailed info about GPU
b553c7dd96a : radv: fix null memcpy and zero-sized malloc
b50ae770144 : radv: align pipeline cache entry and header sizes
4f08af6766c : radv: don't pass null to _mesa_sha1_update
30fca3b2e65 : nir: fix memory leak in nir_cf_list_clone
27ec38d7468 : nir: fix potential left shift of a negative value
391eeb74435 : util: add a alignof() macro
721cb6cc079 : gitlab: ask inxi output to be in code blocks
e901b901cb6 : radv,aco: report ACO errors/warnings back via VK_EXT_debug_report
c2b1978aa47 : aco: rework the way various compilation/validation errors are reported
bc723dfda7b : aco: rename DEBUG_VALIDATE to DEBUG_VALIDATE_IR
709dffa8566 : anv: null check for buffer before reading size
8d38b25788c : util: Explicitly call the unpack functions from inside bptc pack/unpack.
edf0aeb3cd2 : util: Expose rgba unpack/fetch functions as external functions as well.
9d503b36ca2 : iris: Drop buffer support in resource_from_handle
c54bb23967b : iris: Add and use iris_resource_configure_main
51e42e21839 : iris: Move size/offset calculations out of configure_aux
8b2fc919598 : iris: Drop old comment on clear color BO allocation
fd3c20674ea : iris: Drop unused resource allocation optimization
2555321a109 : iris: Drop iris_resource_alloc_separate_aux
0dc0a79a581 : egl: drop another indentation level in _eglFindDisplay() by inverting an if
8b2fc1d1b5a : egl: drop an indentation level in _eglFindDisplay() by replacing break/if with a goto
b5d36e9cb6c : gitlab-ci: fix quoting of variables passed down to bare-metal runners
72fac11ca37 : gitlab-ci: fix testing whether a variable with a given name is set or not
64fb3e6def2 : docs: update calendar and link releases notes for 20.1.6
8be321f30ab : docs: add release notes for 20.1.6
bd38ea77e80 : v3d/compiler: add v3dv_prog_data_size helper
a880f97d593 : compiler/types: Allow interfaces in get_explicit_type_for_size_align
df9596353a6 : nir/large_constants: Handle incomplete derefs
9f3c595dfc4 : nir/find_array_copies: Handle cast derefs
a0a0bcfa263 : nir/builder: Add a nir_iand_imm helper
ac95bb45e82 : nir: Initialize nir_ssa_def::live_index
8f7784ee8da : clover/nir: Use the correct address mode for shared
b2226f7a98d : clover/nir: Stop computing the global address format twice
884d2021d9a : clover/nir: Stop setting ubo_addr_format
5ef9c110d5d : nv50/ir/nir: support load_work_dim
080bee33da1 : nvc0: handle nr being 0 in nvc0_set_global_bindings
b283fb335b2 : nv50/ir/nir: fix global_atomic_comp_swap
4403176201f : clover/nir: support int64 atomics if the device supports it
38e904f9293 : nv50/ir/nir: assert on unknown alu ops
ada8c76cca1 : nve4: fix uploading unaligned sized input buffers
918e444f045 : clover/nir: Call vars_to_explicit_types for shared memory
1e7c2d1862e : nir/glsl: Add glsl_get_cl_type_size_align helper
a27823ef2cd : freedreno/ir3: Fix assertion failures dumping CS high full regs.
ce335dcb192 : freedreno/cffdec: When .mergedregs is set, don't count half regs.
803ec06b1b3 : freedreno/ir3: Fix compiler warning from the setjmp fails path.
c1a6e345739 : nir/lower_input_attachments: Support loading layer id via gl_ViewIndex
76f711d09d2 : tu: Use an input for the layer when lowering input attachments
c77716294b7 : radv: Use an input for the layer when lowering input attachments
d243bf10326 : nir/lower_input_attachments: Support loading layer id as an input
e72895767bc : nir/lower_input_attachments: Refactor to use an options struct
340c73d4efd : nir/spirv: Add the option to keep ViewIndex as an input
c1e69570331 : Revert "gitlab-ci: reuse container_post_build when building the test images"
7e3a788bd30 : freedreno/a6xx: fix occlusion query with more than one tile
5550bc04230 : freedreno/a6xx: only generate streamout for draw pass shader
ee7949b0645 : freedreno/registers: SC_WAIT_WC is not a6xx
60dae984568 : nir/opt_remove_phis: optimize out phis with undef
326eb567189 : egl/x11_dri3: implement EGL_KHR_swap_buffers_with_damage
eae181e3eb9 : egl/x11_dri3: enable & require xfixes 2.0
6c9cf84409b : ci: Run deqp-gles2 on RadeonSI
ff3ea3b3bb3 : pan/mdg: Fix auxiliary load/store swizzle packing
529f79d639d : pan/mdg: Fix printing of r26 ld/st sources post-RA
14e774929ec : pan/mdg: Identify barrier out-of-order field
af97331aba5 : pan/mdg: Handle 32-bit offsets from store_shared
06c31031e7e : pan/mdg: Ensure barrier op is set on texture
415eb43fd5f : panfrost: Fix shared memory size computation
39bf1fb3221 : panfrost: Fix WRITES_GLOBAL bit
8626d4cbef0 : android: freedreno: Another build fix
41bb6459d3a : radv: restrict exported symbols with static llvm
a457256e2d6 : freedreno: Destroy syncobj too when destroying fence
b08fcab44d7 : gitlab-ci: reorder container_post_build call for arm64_test image
40ab6d77c06 : gitlab-ci: reuse container_post_build when building the test images
1cf7a3968f3 : panfrost: Hoist assert from bind to create
3b129dd335c : panfrost: Remove useless comment
a2e41590293 : panfrost: Hoist add_fbo_bo call
433fa39c2e6 : panfrost: Drop QUADS primitive convert
4b21c8b15f0 : panfrost: Drop panfrost_invalidate_frame
1362371a96e : panfrost: Drop ZSA null checks in draws
ec35159fba5 : panfrost: Drop rasterizer null checks in draw calls
e46d4fe8bc4 : panfrost: Decontextualize rasterizer
d26f62c6670 : radv: track and report if a logical device is lost
c9c53dade01 : ci: Update kernel used in LAVA to 5.8-based drm-misc
91cd7fe9784 : ci: Fix URL to imagediff page in traces dashboard
922217431c6 : ci: Test Panfrost with more traces
7d5f4d3f709 : ci: Split traces.yml file per driver
eb787773b2d : llvmpipe/nir: lower some more packing at nir level.
95d611e036a : llvmpipe: lower mul 2x32_64
25ba200985d : llvmpipe: lower cs local index from id
3cc5b75577d : gallivm/nir: split tex/sampler indirect offsets
e616223024d : gallivm/nir: fixup compact TCS variable storage.
597d0e9b5fd : gallium/nir/tgsi: add support for compact variables
fe9667e336b : llvmpipe: lower uadd_carry/usub_borrow.
7893dfa247c : gallivm/sample: fix lod query on array textures.
da4f2215aac : gallivm/nir: add imod support
407fa329a4b : gallium/nir/tgsi: reindent some code in the nir->tgsi info (v2)
e137bbb87fa : llvmpipe/cs: update compute counters not fragment shader.
6c7383d315f : vallium: fix input attachment lowering variable shadowing
e0e9712a4d8 : freedreno: support GL_EXT_semaphore
f6187aa1c35 : freedreno: Enable GL_EXT_memory_object and GL_EXT_memory_object_fd
e3c39e50522 : freedreno: Implement pipe screen's get_device/driver_uuid()
6bef126c621 : freedreno: implement pipe screen's resource_from_memobj
03fdf418a58 : freedreno/layout: Move hard-coded minimum width for UBWC to a macro
536ec9d7f5a : freedreno: Refactor fd_resource_create_with_modifiers() into a helper
0eecd3d6846 : freedreno: Implement memory object create/destroy for GL_EXT_memory_object
e48f27ee645 : st: Pass TextureTiling option from texture to memory obj
b479de8537a : spirv: Don't emit RMW for vector indexing in shared or global
f038b3a1361 : radv: Fix handling of attribs 16-31.
0067f899200 : radv: Override the uniform buffer offset alignment for World War Z.
a1d4721e21b : driconf: Support selection by Vulkan applicationName.
f88b9eb9c5f : egl/android: Add support for CrOS buffer info perform op
acb235c0c8a : egl/android: Use droid_create_image_from_prime_fds() in get_back_bo()
cad9d42bb4e : egl/android: Move droid_create_image_from_prime_fds() function up
5c8b67ed0c4 : egl/android: Simplify droid_create_image_from_name() path
d47b6f330cf : egl/android: Drop unused ctx argument
9cc788f0ffc : egl/android: Look up prime fds in droid_create_image_from_prime_fds()
972f36d8fa6 : egl/android: Call createImageFromDmaBufs directly
7c98066e805 : freedreno: Add afuc regression test
d145fcc1c1c : freedreno/afuc: Install asm/disasm
f0b87186df2 : freedreno/afuc: Make 0 a valid number
66dd248593b : freedreno/afuc: Handle xmov modifiers
b2b19234d81 : freedreno/afuc: Add iret
a2c14ac070b : freedreno/afuc: Handle setsecure opcode
0acc394486f : freedreno/afuc: Fix printing preemptleave on a5xx
165009bc702 : spirv: Add support for the CL Round instruction
6d28270968e : meson: Make some warnings handled as errors with MSVC
45f22528792 : meson: Add MSVC narrowing-int-to-char warnings
d8edf8e383d : Revert "CI: Disable Panfrost T720/T760 CI"
e229e79464e : mesa: utils: add "force_gl_vendor" option support
fcc7a1e7b6d : gallium/aux: reorder vertex attributes in triangle fans according to PV
f5cce8929ad : gallium/indices: translate primitive-restart values
21952f1400a : gallium/indices: introduce u_primconvert_config
c2e9cd3f773 : gallium/indices: implement prim-restart for triangle fans
dfc0a629942 : gallium/indices: use prim_restart-helper for polygon
3aa4f64e8d5 : gallium/indices: implement prim-restart for line-loops
ac96225eb0e : gallium/indices: generalize primitive-restart logic
2122b902b80 : gallium/indices: don't expand prim-type for 8-bit indices
0c85d6c523f : gallium/util: factor out primitive-restart rewriting logic
b6ebf6eba95 : spirv: Only require bare types to match when copying variables
16f1d8b3910 : glsl: fix crashes on out of bound matrix access using constant index
7dcb1d272fa : st/mesa: Replace UsesStreams by ActiveStreamMask for GS
ab5a36b342f : meson: fix trivial s/dir/dri/ typo
9ef192c100b : CI: Disable Panfrost T720/T760 CI
5a26015764e : st/wgl: do not reject PFD_SUPPORT_GDI
ac9c94fa14f : CI: Skip another flaky GS test on softpipe
e513d8d8cd1 : CI: Skip flaky CS test on VirGL
3e447c1ad2d : CI: Disable Panfrost T860 and AMD Stoney tests
80163bbec3a : nir/vtn: Support OpOrdered and OpUnordered opcodes
81e6ad82986 : nir/vtn: Handle LessOrGreater deprecated opcode
c349e350340 : nir/vtn: Support SpvOpIsFinite via fisfinite
af59e4c4004 : nir: Add fisfinite op
e6e6f52206e : nir/vtn: Support SpvOpIsNormal via fisnormal
9ebbed6ddcc : nir: Add fisnormal op
199bea0fd80 : nir: Fix i64tof32 lowering
f9e773b9205 : llvmpipe: enable GL 4.5
2e40b2c1550 : llvmpipe/blit: for 32-bit unorm depth blits just copy 32-bit
18e464cfc05 : compiler/nir: Add new flags to lower pack/unpack split instructions
9e9d28007a4 : mesa: Move ATTRIBUTE_NOINLINE for glsl_to_tgsi_visitor::visit_expression for MSVC
c60cea0daa2 : glsl/test: Don't run whitespace tests in parallel
aeba69deaa5 : drisw: Port the MIT-SHM check to XCB
ee905aa3a01 : nir/vtn: CL SPIR-V callers should specify address modes
a097bf160a9 : nir/builder: Make nir_get_ptr_bitsize take a nir_shader
627c8e1640b : nir: Add nir_address_format_32bit_index_offset_pack64
113458d3720 : nir: Add nir_address_format_32bit_offset_as_64bit
a1ed83fddd7 : nir: Optimize mask+downcast to just downcast
fd9b33d5167 : nir: Fix serialize/deserialize of void samplers/images
c17b58a9e60 : glsl: Add 'bare' shadow sampler type
418c4c0d7d4 : compiler/nir: extend lower_fragcoord_wtrans to support VARYING_SLOT_POS
7aaddf1a342 : compiler/nir: rewrite lower_fragcoord_wtrans to use nir_lower_instructions
c9f4b14ac6d : Revert "CI: temp disable t720/t760 jobs."
d79c946fb35 : nv50/ir/nir: rework indirect function_temp handling
fd265bb4f1f : panfrost: Update CI expectations
7a13351234c : panfrost: Drop union mali_attr
4e3fe54e2e0 : panfrost: Drop hand-rolled pandecode for attribute buffers
ec58cda5da0 : panfrost: Use packs for varying buffers
9732b64862f : panfrost: Remove mali_attr_meta
eb2762a837d : pan/bit: Use packs for Bifrost unit tests
7ef205dabd4 : panfrost: Use MALI_ATTRIBUTE_LENGTH
59fa26902d5 : panfrost: Use pack for general varying
6c850637f5a : panfrost: Use pack for XFB varying
40b4ee9426f : panfrost: Factor out general varying case
b805cf9b1f4 : panfrost: Pass varying descriptors by reference
d5a264facfd : panfrost: Reword comment
44397c580cc : panfrost: Use packs for vertex built-ins
e646c861fc6 : panfrost: Use packs for vertex attribute buffers
c9bb5dc911a : panfrost: Inline panfrost_vertex_instanced
e9dc2251220 : panfrost: Hoist instance_shift/instance_odd fetch
27f8b879cce : panfrost: Use packs for attributes
6caf789c07a : panfrost: Move attr_meta emission to the draw routine
8236fa3ff16 : panfrost: Make attribute-buffer map explicit
9cc81ea0c20 : panfrost: Simplify offset fixup proof
4fc90f7c3c5 : panfrost: Use better packs for blits
3e7fd2a0346 : panfrost: Add XML for attribute buffers
76de3e691c6 : panfrost: Merge attribute packing routines
2c8a722b85e : panfrost: XMLify attributes
cdc3276317d : panfrost: XMLify mali_channel
668ec24bfdb : panfrost: Squash 22-bit format field in attr_meta
c5f18ce144f : panfrost: Drop NXR format
e03622e50fc : panfrost: Set STRIDE_4BYTE_ALIGNED_ONLY
350dd2a36dc : pipebuffer: Remove unused buffer event in slab bufmgr
8a012f429de : nir: handle load_input_vertex in nir_get_io_offset_src
83953f9d4d4 : nir: remove nir_strip stub declaration
f3a9781ee19 : compiler: add glsl_print_type
b7c04b1790f : ac/llvm: handle static/shared llvm init separately
916110e17f2 : st/mesa: Enable clip planes lowering for geometry shaders
584f27326c1 : st/mesa: factor ucp-lowering logic into helper
ff4c991fd1c : compiler/glsl: Initialize local variable to zero to fix MSVC RTC error
b38879f8c5f : vallium: initial import of the vulkan frontend
8004fa9c950 : vulkan/wsi: add sw support. (v2)
5a9eba4acd0 : util/format: add some ZS helpers for vallium
3abf548270b : gallivm/nir: add load push constant support
94e4a17f29b : llvmpipe: add support for memory allocation APIs
ecb617a6a75 : gallium: add a resource flag to say no over allocation.
e6c7ca218d7 : gallium: add an interface for memory allocations.
50b039590e1 : radv: Use getter instead of setter to extract value.
09196355b2b : gallium: Use unpack_rgba() instead of fetch_rgba in translate_generic
5b8d67cb64c : util: Move fetch_rgba to a separate function table.
9cc84369b70 : util: Mark the format description getter functions as const.
35b22b5da02 : util: Make all 3 fetch_rgba functions occupy the same function slot.
80babbbf7ea : uitl: Add R1_UNORM to the list of noaccess (no pack/unpack) formats.
6668d7a5f36 : egl: drop unused egldriver.h header
1f01fa11d78 : egl: drop now empty egldriver.c
890d0334c15 : egl: inline _eglInitializeDisplay() into eglInitialize()
0e7ae395e72 : egl: inline _eglGetDriverProc() into eglGetProcAddress()
735b35e34a8 : egl: drop unused ${drv}_driver()
c74628fd1e5 : egl: replace `&_eglDriver`/`NULL` tested against `NULL` with simple `true`/`false`
37be01bff77 : egl: drop unused _EGLDriver from MesaGLInteropEGL{QueryDeviceInfo,ExportObject}()
5eb5847d487 : egl: replace replace _EGLDriver with _EGLDisplay->Driver in eglapi.c
372c6c42af1 : egl: replace _EGLDriver with _EGLDisplay->Driver in _eglGetSyncAttrib()
b9fb63ab03c : egl: drop unused _EGLDriver from _eglSurfaceAttrib()
b981babb937 : egl: drop unused _EGLDriver & _EGLDisplay from _eglQueryContext()
3ef8aacb60e : egl: drop unused _EGLDisplay from _eglSetDamageRegionKHRClampRects()
0345a614629 : egl: drop unused _EGLDriver from _eglGetConfigs()/_eglChooseConfig()/_eglGetConfigAttrib()
67c745644fb : egl: drop unused _EGLDriver from SetBlobCacheFuncsANDROID()
1bbb0c7689b : egl: drop unused _EGLDriver from QueryDmaBuf{Formats,Modifiers}EXT()
a71dcd2dc2a : egl: drop unused _EGLDriver from ExportDMABUFImage{,Query}MESA()
429e9369480 : egl: drop unused _EGLDriver from QueryBufferAge()
155541bc025 : egl: drop unused _EGLDriver from PostSubBufferNV()
f010568ea25 : egl: drop unused _EGLDriver from CreateWaylandBufferFromImageWL()
845a37ce355 : egl: drop unused _EGLDriver from {Bind,Unbind,Query}WaylandDisplayWL()
9d5162eddf8 : egl: drop unused _EGLDriver from {Create,Export}DRMImageMESA()
692b9c6ed0c : egl: drop unused _EGLDriver from DupNativeFenceFDANDROID()
f49805c441a : egl: drop unused _EGLDriver from {Create,Destroy,ClientWait,Wait,Signal}SyncKHR()
740ec08f21c : egl: drop unused _EGLDriver from {Create,Destroy}ImageKHR()
a7d15d2ae3a : egl: drop unused _EGLDriver from GetProcAddress()
b8d1c4647f2 : egl: drop unused _EGLDriver & _EGLDisplay from WaitNative()
4e65469c706 : egl: drop unused _EGLDriver from WaitClient()
648f603c356 : egl: drop unused _EGLDriver from SetDamageRegion()
d202fd6596c : egl: drop unused _EGLDriver from CopyBuffers()
82035b2e3db : egl: drop unused _EGLDriver from SwapBuffers{,WithDamageEXT,RegionNOK}()
347840cf436 : egl: drop unused _EGLDriver from SwapInterval()
2f4a6ad3b32 : egl: drop unused _EGLDriver from {Bind,Release}TexImage()
982ac69e3f8 : egl: drop unused _EGLDriver from QuerySurface()
1a17f1db555 : egl: drop unused _EGLDriver from MakeCurrent()
6b4c474ed7d : egl: drop unused _EGLDriver from Create{Window,Pixmap,Pbuffer}Surface() & DestroySurface()
f27a32a7927 : egl: drop unused _EGLDriver from {Create,Destroy}Context()
435ad514163 : egl: drop unused _EGLDriver from Terminate()
ad61d4f1461 : egl: drop unused _EGLDriver from Initialize()
e87e68d836e : egl: replace _EGLDriver with _EGLDisplay->Driver in _eglQuerySurface()
f3aa7b2e1b1 : egl: replace _EGLDriver param with _EGLDisplay->Driver in dri{2_x11,3}_create_window_surface()
485f8f89f90 : egl: replace _EGLDriver param with _EGLDisplay->Driver in _eglReleaseDisplayResources()
a76423e481a : spirv/vtn_cfg.c: Include util/debug.h for env_var_as_boolean.
430e3310e2a : llvmpipe: only read 0 for channels being read
f1001a38275 : CI: temp disable t720/t760 jobs.
031f9e17d2c : anv: don't fail userspace relocation with perf queries
dc667b1f192 : nv50/ir/nir: fix smem size
384c4df23da : clover/nir: fix mem_shared by using address_format_32bit_offset
aa8661141a0 : android: util/format: fix generated sources rules
b41e74ae4a7 : spirv: Add a MESA_SPIRV_FORCE_UNSTRUCTURED environment variable
217def3ac67 : spirv: parse unstructured CFG
467b90fcc46 : spirv: extract switch parsing into its own function
96dff31bc8f : spirv: Move the emit a 'return value' store logic into own function
4638de8b1b3 : nir/lower_goto_if: Add some debug prints
d57573dcd4a : nir/lower_goto_if: Add a route::outside set
d2bf850672b : nir/lower_goto_if: Replace a tripple loop with a double loop
b892d473b4e : nir/lower_goto_if: Add a block_for_singular_set helper
193765e26ba : nir/lower_goto_if: Sort blocks in select_fork
0fad20f21b3 : nir/lower_goto_if: Rework some set union logic
d1617985896 : nir/lower_goto_if: Rework handling of skip targets
2455d03c311 : nir/lower_goto_if: Use util/list instead of exec_list
f69d732fcab : nir/lower_goto_if: Clean up ralloc usage
202b4df4aee : nir/lower_goto_if: Document some data structures
b273611bb17 : nir: Add a structurizer
025bdbac3e0 : nir: Add goto_if jump instruction
92db942fc6a : nir: Add and use nir_foreach_block_unstructured helpers
4768ea1a77a : nir: Add a structured flag to nir_shader
19f35735a09 : spirv: rename vtn_emit_cf_list to vtn_emit_cf_list_structured
16f858968f2 : util/set: add _mesa_set_intersects
acf756a64fe : android: panfrost: Redirect cmdstream includes through GenXML (v2)
92f65e28fee : turnip: add missing tu_bo_list_add in CmdWriteTimestamp
ddac5933f8f : turnip: call packing functions directly for pack_gmem_clear_value
201331edbfe : turnip: rework format_to_ifmt
aa5ebf0a6dc : turnip: fix CmdBlitImage with D32_SFLOAT_S8_UINT
f83e89507de : turnip: delete a blit_image TODO that has already been resolved
2ca1ccc18d8 : turnip: remove dead tu_minify/typed_memcpy functions
99372547be9 : android: panfrost/bifrost: add libpanfrost_lib static dependency
bce1a7e97fc : android: panfrost: Redirect cmdstream includes through GenXML
0980d1d5ab0 : radv: Clean up setting the surface flags.
d19bc94e4eb : radv: When importing an image, redo the layout based on the metadata.
a0d67b7a1c3 : anv: add no reloc flags on empty and simple bo paths.
00b9a3443ba : anv: Mark anv_dump_{start,finish} as PUBLIC
f024bc8314c : zink: invalidate pipeline hash on more changes
65d7172d171 : util/macros: Add ATTRIBUTE_NOINLINE definition for MSVC
58af31186a8 : u_debug_stack_test: Fix MSVC compiling by using ATTRIBUTE_NOINLINE
493298528a8 : iris: Make iris_bo_import_dmabuf take a modifier
c111e9099ce : iris: Don't call SET_TILING for dmabuf imports
0c97e601a42 : turnip: implement VK_EXT_custom_border_color
84ed2d0980b : util/format: expose generated format packing functions through a header
a322924d9cf : panfrost: add missing dependency on midgard_pack.h
8557b1a8ebe : panfrost: Fix border colour
8277334f397 : nir/lower_idiv: Port recent LLVM fixes to emit_udiv
d452c04aa19 : aco: do not set valid_mask for POS0 exports on GFX 10.3
0c621dcf0ed : panfrost: XMLify enum mali_format
78445ce6954 : panfrost: XMLify exception access
99d17fb771b : panfrost: XMLify MSAA writeout mode
c9bdba26b0c : panfrost: XMLify Block Format
8c1ac96eb6e : panfrost: Drop unused mali_channel_swizzle
ad0b32cdbd5 : panfrost: XMLify Bifrost textures
f008a6314c6 : panfrost: XMLify Midgard textures
b10c3c869d9 : panfrost: XMLify Bifrost samplers
f74186baa5e : panfrost: XMLify Midgard samplers
c4c8c8e8fbd : panfrost: Don't mask coverage mask to 4-bits
6afd4addefa : panfrost: Simplify depth/stencil/alpha
1675d92d663 : panfrost: Simplify zsa == NULL case
931e7b4c7a1 : panfrost: XMLify stencil test
fa949678c19 : panfrost: XMLify UBOs
7f487e087f9 : panfrost: XMLify viewport
ef20691e3d8 : panfrost: XMLify wrap modes
e9ca3204619 : panfrost: XMLify stencil op
d182a6057fd : panfrost: XMLify mali_func
32dbc80979e : panfrost: XMLify draw_mode
4b7056b8c8a : panfrost: XMLify job_type
d2ddd4d5656 : pan/decode: Add helper to dump GPU structures
88dc4c21e6c : panfrost: Redirect cmdstream includes through GenXML
1ad921956d8 : panfrost: Build midgard_pack.h via meson
75cc5b8c292 : panfrost: Adopt gen_pack_header.py via v3d
9cb3a9e72eb : panfrost: Add stub midgard.xml
33e69203d2a : util: Fix up indentation in the generated format tables code.
9fd0f455af7 : util: Change a codegenned switch statement to a nice little table.
4064a6cd207 : util: Split the pack/unpack functions out of the format desc.
6723addd8a7 : docs: update calendar for 20.2.0-rc2
6de5acdf4fd : docs: update calendar for 20.2.0-rc1
4c84600afaf : radeonsi: fix compute-based culling with VERTEX_COUNTER_GDS_MODE == 1
2b78cb2e003 : radeonsi: disable NGG culling on gfx10.3 because of hangs
61042b1bdb1 : zink: handle more draw modes
ced9e6e3e5c : zink: change pipeline hashes to index based on vk primitive type
2701f887fc3 : anv/nir: Unify inputs_read/outputs_written between geometry stages
2a1217513e1 : panfrost: Implement panfrost_query_dmabuf_modifiers
24c921b1b5c : panfrost: Ensure AFBC slices are aligned
4d0241dfed3 : panfrost: Allocate enough space for tiled formats
8c0cb56fd9e : panfrost: Enable YTR where allowed
d285ea6467d : panfrost: Implement YTR availability check
acb8dcfebdd : panfrost: Choose AFBC when available
c54d45dd90a : panfrost: Import staging routines from freedreno
348d374d013 : panfrost: Respect modifiers in resource management
56f9cc99487 : panfrost: Account for modifiers when creating BO
965537df2af : panfrost: Use modifier instead of layout throughout
6fed69cde2a : panfrost: Introduce create_with_modifier helper
32bd588fede : panfrost: Remove hint-based AFBC heuristic
340017ec476 : panfrost: Set `initialized` more conservatively
22777025d4a : gallium/dri2: Support Arm modifiers
37872edf6fc : zink: print error when getprocaddr fails for extension functions
371f6f42ad4 : radv: Update CI expectations for the recent descriptor indexing regressions.
3d7d76c1525 : iris: Add support for MESA_SHADER_KERNEL in the disk cache
65eeb06a7f7 : iris: Upload kernel inputs with system values
f5e7be386ff : iris: Copy dest size from the original intrinsic in setup_uniforms
43429efc61e : iris/disk_cache: Stop assuming stage == cache_id
6dfe41c54e2 : iris: Add a kernel_input_size field for compiled shaders
e39326e617d : iris: Use blob_write_uint32 for num_system_values
003b04e266a : intel/compiler: Allow MESA_SHADER_KERNEL
e2b6ccbdadd : intel/compiler: Use C99 array initializers for prog_data/key sizes
8e1de8e5ac9 : intel/cs_intrinsics: Handle 64-bit intrinsics
8d62735b470 : iris: Add support for serialized NIR
baa4cf9b8ed : iris: Implement set_global_binding
17280a8ef1a : iris: no-op implement set_compute_resources
ac6e207ee07 : gitlab-ci: test Fossilize with GFX1030
431a3cf239e : radv/winsys: add null winsys entries for Sienna Cichild/Navy Flounder
638a09b827f : radv: fix emitting the border color pointer on the compute queue
96cfc684e63 : util: Fix memory leaks in unit test.
ef66e02a408 : src/mesa: add GL_NV_half_float extension support (v2)
8abf59ff988 : dri_util: Update internal_format to GL_RGB8 for MESA_FORMAT_B8G8R8X8_UNORM
fdb97d3d291 : aco: execute branch instructions in WQM if necessary
678cb6d248f : nir: nir_range_analysis needs to be updated for vec16
7b4c24eb679 : aco: don't move memory accesses to before control barriers
e4c6204d659 : radv: limit LATE_ALLOC_GS to prevent a GPU hang on GFX10
02562505478 : radv/gfx10: add missing initialization of registers
044b238507b : etnaviv: completely turn off MSAA
5cf7eec6b15 : nir/lower_ssbo: Don't set align_* for atomics
2d010d3dc5f : anv: add a check for depthStencilState before using it
ffc8f2ba4c2 : anv: fix up dynamic clip emission
240c0746d16 : anv: centralize vk to gen arrays
3d6e4a201af : freedreno/decode: try harder to not crash in disasm
cbfce486f2c : freedreno/crashdec: handle section name typos
8d437b21944 : freedreno/ir3: add more disasm stats
7aa74ab7921 : freedreno/ir3: add tracking for # of instructions per category
2cd0c8d8ea1 : gallium/u_transfer_helper: add util functions for doing deinterleaving during map
2368813ce6f : gallium: add pipe_transfer_usage for z/s only mappings
cf52b40fb0b : intel/fs: work around gen12 lower-precision source modifier limitation
ee06e47c5b1 : intel/fs: Assert if lower_source_modifiers converts 32x16 to 32x32 multiplication
166630f7592 : android: pan/bi: Separate disasm/compiler targets
41c9a2e740a : android: pan/mdg: Separate disassembler and compiler targets
b9e58be3479 : android: panfrost: Move pandecode into lib/
de352f58c38 : android: panfrost: Rename encoder/ to lib/
6e705081518 : aco: set constant_data_offset correctly in the case of merged shaders
0f8ef37f653 : radeon/vcn: fix jpeg decode for navi10
e362ccb20c8 : radv: Do not consider layouts fast-clearable on compute queue.
2fa83dc64d7 : radv: Add forcecompress debug flag.
a777b25350c : intel/perf: export performance counters sorted by [group|set] and name
59716e40b0f : intel/perf: split load_oa_metrics
2fbab5a1b39 : intel/perf: fix performance counters availability after glFinish
9fa64803aad : intel/perf: streamline error handling in read_oa_samples_until
03e8b3551cf : intel/perf: fix how pipeline stats are stored
e7e6f709389 : intel/perf: fix calculation of used counter space
6d988ad4a21 : radv: report a better error message when QueueWaitIdle() failed
3691ef55961 : radv: report errors back to the application via VK_EXT_debug_report
cc4b9c2128c : radv: rework the error function helpers a bit
11781c0e49d : radv: report the spirv-nir logs back to the application
ff4f6202be2 : radv: Fix assert that is too strict.
f7e7cf637e1 : radeon/radeon_vce: fix out of target bitrate in CBR mode (H.264)
4975b3ec551 : r600: Enable compute shaders for NIR code path
834a61df4ed : r600/sfn: Force a minimum of 4 GPRs, it seems to fix atomics
3e3068a76a6 : r600/sfn: handle querying SSBO size
ac87cc22053 : r600/sfn: Correct ssbo instruction handling
11a861c78a0 : r600/sfn: correct allocating and emitting of atomics
702619c4126 : r600/sfn: Add a mapping table for atomics
56dedf052f4 : r600/sfn: add r600 specific lowering pass for atomics and use it
df2acf8e26a : r600/sfn: Sort uniforms by binding and offset
a828f6c5139 : r600: Set PIPE_CAP_NIR_ATOMICS_AS_DEREF to true
a03e24aa7fa : gallium + mesa/st: Add PIPE_CAP_NIR_ATOMICS_AS_DEREF and use it
dd003abd2fc : meson: bump required glvnd version
7fbadfc385c : driconf: fix force_gl_vendor description
800816d70be : egl/entrypoint-check: add check that GLVND and plain EGL have the same entrypoints
351d513e30b : egl/entrypoint-check: split sort-check into a function
04bd58ff79e : Correct a typo in threads_win32.h
e3069c42577 : pick-ui: specify git commands in "resolve cherry pick" message
b238d17a02f : zink: Fix 32-bit compilation
08f3dcf2f6e : i965: add support for force_gl_vendor
ab92c117809 : freedreno/ir3: don't install ir3_compiler cmdline tool
3b6e8670f81 : freedreno/registers: add some missing regs to build
1e28745bc0d : meson/freedreno: Fix lua requirement
0cdd411b6d7 : radeonsi: various fixes for gfx10.3
e2e700f6053 : radeonsi: remove the NGG hack decreasing LDS usage to deal with overflows
97456e847e0 : radeonsi: add a common function for getting the size of gs_ngg_scratch
68b3e92fef0 : radeonsi: don't count unusable vertices to the NGG LDS size
64c741ffb7a : radeonsi: fix applying the NGG minimum vertex count requirement
7a468fc0f6a : radeonsi: increase minimum NGG vertex count requirement per workgroup on gfx 10.3
633d2aa9157 : radeonsi: use the same units for esgs_ring_size and ngg_emit_size
b6fb09fd843 : radeonsi: use correct wave size in gfx10_ngg_calculate_subgroup_info
61c671c97e8 : Revert "radeonsi: honor a user-specified pitch on gfx10.3"
15bd3f3712a : ac/gpu_info: set num_tiles_pipes on gfx10+ too
9333a8570d2 : radeonsi: enable ETC2 hw acceleration on Raven2
1185b3f32d9 : zink: pre-hash gfx-pipeline-state
7be12df5e62 : zink: rename zink_gfx_program::stages to 'modules'
6196f2aa937 : zink: always compile shaders in pipeline order
c312299316c : zink: start using per-stage flags for new shaders, refcount shader modules
76d3645dd2e : zink: use ZINK_SHADER_COUNT instead of PIPE_SHADER_TYPES - 1 everywhere
0f059d550bd : zink: split up creating zink_shader objects and VkShaderModule objects
a03d17ede77 : zink: refcount zink_gfx_program objects
8772c693c5a : zink: adjust zink_shader struct to contain full streamout info
e481d3e2ed0 : zink: move shader state methods for pipe_context into zink_program.c
d83be29a533 : intel/dump_gpu: add an option to capture a single frame
a6a5b0e52eb : intel/dump_gpu: fix --platform option
9f0db069d3a : anv: track the current frame and write it into the driver identifier BO
42cb068d9f1 : intel/dump_gpu: only map in GTT buffers not previously mapped
22b512ea5b1 : intel/dump_gpu: add an only-capture option
f0e13827aab : intel/dump_gpu: set default device_override
c4bfa6dfbb1 : intel/dump_gpu: further track mapping of BOs
63c90acc9eb : intel/dump_gpu: only write BOs mapped by the driver
54c68498d4c : zink: set primitive restart cap
5959178381f : zink: use util_draw_vbo_without_prim_restart for unsupported prim modes
f4583b40863 : zink: move 8bit index handling out of u_primconvert path
5edaf081cdb : zink: basic primitive restart support for strip/fan topologies
8531830038d : radv: Add ETC2 support on RAVEN2.
bea8930468e : radv: allow to force-enable LLVM internally for a specific shader stage
e63a7882a0a : etnaviv: call nir_lower_bool_to_bitsize
c5b23196288 : panfrost: Drop compiler cmdstream deps
1d0b3ef051e : panfrost: Treat texture dimension as first-class
5a3088e85f2 : panfrost: Inline max rt into compilers
54f96544ec2 : pan/bi: Drop use of MALI_POSITIVE
c94013c8194 : panfrost: Add panloader/ to .gitignore
52e3a67bb1a : panfrost: Reduce bit dependency to disassembly only
14bb72c68b4 : pan/bi: Separate disasm/compiler targets
b792d613e65 : pan/mdg: Separate disassembler and compiler targets
d62a6e7c5f6 : panfrost: Move pandecode into lib/
1c62b5528ab : panfrost: Rename encoder/ to lib/
956b09653cc : panfrost: Don't export exception_status
4ddc6e543cb : panfrost: Remove panfrost-misc.h
64f3c9da87b : panfrost: Inline panfrost-misc.h into panfrost-job.h
ebf7e87f2cd : pan/decode: Remove shader replacement artefact
e4df95bf9fd : panfrost: Move format stringify to decode.c
b80e753940a : panfrost: Remove blend prettyprinters
b43bcb05a17 : anv: fix incorrect realloc failure handling
21b47cbd996 : aco: fix C++11/C++14 compilation
782ba8d3ae5 : st/mesa: Treat vertex outputs absent in outputMapping as zero in mesa_to_tgsi
a92cfa66b4e : Bump development version and clear new_features
7f06d194fd3 : anv: Advertise shaderIntegerFunctions2
9e397956b09 : panfrost: signal syncobj if nothing is going to be flushed
c6aadbae715 : radv: Don't use both DCC and CMASK for single sample images.
e2c614a415b : appveyor: Use Python3.
0f9fb7ffaae : appveyor: Upgrade pip.
2e665458a90 : util: Fix SCons build.
56ab105182e : freedreno: Add more asserts for DST_OFF/NUM_UNIT in indirect const uploads.
3e970de3603 : freedreno: Increase the NUM_UNIT on compute's consts in indirect dispatch.
f07e25bc6d8 : freedreno/ir3: Clean up instrlen setup.
8f637d66cc1 : freedreno: Split ir3_const's user buffer and indirect upload APIs.
154299934d8 : freedreno: Rename emit_const_bo() to emit_const_ptrs().
51acfe22306 : freedreno/ir3: Simpify the immediates from an array of vec4 to array of dwords.
e873c4da08d : freedreno/ir3: Merge the redundant immediate_idx/immediates_count fields
5e922fbc160 : glsl_to_nir: fix bitfield_extract with 16-bit operands
92f5e94a937 : glsl: improve precision determination for calls
282a1e6288f : glsl: don't lower to mediump for desktop OpenGL
01e00856375 : glsl: don't create conversion opcodes for array types
5020403c703 : glsl: don't lower atomic functions to mediump
93076f60d3a : glsl: don't inline intrinsics for mediump
48a6255186d : glsl: fix constant expression evaluation for 16-bit types
f2d5f4851ab : glsl: lower_precision - fix assertion failure with dereferences of constants
a88fd7bfdc6 : docs: update calendar and link releases notes for 20.1.5
2d3f81f3207 : docs: add release notes for 20.1.5
a4c4e0103a5 : glsl: remove LowerPrecisionTemporaries
c4e0cae90c5 : gallium: replace 16BIT_TEMPS cap with 16BIT_CONSTS
0a763c0c86b : glsl/lower_precision: split out const lowering
4f060549be4 : freedreno/ir3: lower local_index using local_id
e0947903fc7 : freedreno/ir3: ir3_cmdline updates
283ad85944b : radeonsi: call nir_split_array_vars/shrink_vec_array_vars/opt_find_array_copies
47beee2eb3f : radeonsi: reorder NIR optimizations
0294eaed809 : radeonsi: extend workaround for KHR-GL45.texture_view.view_classes on gfx9
caa98246a0e : st/mesa: optimize DEPTH_STENCIL copies using fragment shader
141b295311a : freedreno: allow fence_fd fences to be recycled
07a49bf5976 : radeonsi: disable SDMA on gfx9
879444a957d : ci: Add a build test for the Android platform
db504c464f8 : radv/android: Remove unused variable
a7fe711a30f : vulkan: Allow global symbol HMI for Android
6b3f56f0997 : anv: Add stub for anv_gem_get_tiling() for Android
ff0dbf20961 : anv: Pass device to setup_gralloc0_usage for error reporting
5096ebf9549 : meson: Define ANDROID and ANDROID_API_LEVEL when compiling for Android
e05e60b2301 : turnip: Make tu_android.c compile again
a725899c3f8 : mapi: Mark TLS symbols as optional in glapi-symbols.txt
932f51d5934 : ci: Include enough Android headers to let us compile test EGL
5ae7098ebab : gallium/android: Rewrite backtrace helper for android
d0d14f3f648 : util: Add unit test for stack backtrace caputure
848e7b947d0 : util: Move stack debug functions to src/util
e487043fd09 : gallium: Switch u_debug_stack/symbol.c to util/hash_table.h
e1a58ae7c46 : mapi/test: Change type to unsigned for offset
c8749305f26 : egl/android: Remove unused variable
24b80f8bb9c : amd/llvm: Reorder LLVM headers
1541ef636b2 : ci: Use a rootfs tarball for NFS root, instead of a ramdisk (for LAVA)
8fab7d738e8 : radv: set BYPASS_VTX_RATE_COMBINER_GFX103 on GFX 10.3
05b09d65493 : radv: fix sample shading on GFX 10.3
8b3682310ce : radv: increase minimum NGG vertex count requirement per workgroup on GFX 10.3
22c80798299 : radv: do not honor a user-specified pitch on GFX 10.3
7f25f1f1067 : nir/lower_tex: handle query lod with nir_lower_tex_packing_16 at lower_tex_packing
6e2e77557ee : radv/llvm: enable VK_KHR_memory_model
4f3630b36ab : ac/nir: fix coherent global loads/stores
4640e7da04a : ac/nir: consider an image load/store intrinsic's access
da38e99edad : radv/aco: enable VK_KHR_memory_model
389c95a8890 : spirv: set ACCESS_COHERENT for ssbo/global/image atomic load/store
71572ebb32e : nir/lower_tex: skip lower_tex_packing for the texture samples query
1938e2596f5 : freedreno/computerator: Set SP_MODE_CONTROL to the same value as vulkan/GL
c92ae9d3ef8 : freedreno/a6xx: Document the bit for the magic 32bit-uniforms-as-16b mode.
db25c18f333 : freedreno/ir3: Fix the type of half-float indirect uniform loads.
13b3c401a41 : nir: Print the constant data size associated with a shader.
041bae28c67 : nir: Add a little more docs about NIR's constant_data.
2e833b16bca : nir/lower_amul: Use num_ubos/ssbos instead of recomputing it.
add2b44ab69 : turnip: Only include msm_drm in tu_drm.c
4b9c0cd821a : turnip: Move remaining drm code to tu_drm.c
7dfeae1a457 : turnip: Collapse some tu_drm wrappers
59e5f95bdcc : turnip: Move tu_bo functions to tu_drm.c
270599cc1e7 : turnip: Move device enumeration and feature discovery to tu_drm.c
d33f46e08b7 : anv: fix allocation of custom border color pool
fea3e498c31 : aco: replace MADs in isel with FMA on GFX10.3
41c901b7df9 : aco: disable SMEM stores on GFX10.3
b811b1d083f : aco: update aco_opcodes.py for GFX10.3
07250a92daf : aco: implement subgroup shader_clock on GFX10.3
a5303a3cbea : aco: update vgpr_alloc_granule for GFX10.3
37988b5b8ed : aco: fix max_waves_per_simd on Polaris, VegaM and GFX10.3
c68fba9bba1 : aco: update bug workarounds for GFX10_3
4f1242a4d8c : aco: don't create v_mad_f32 on GFX10.3
5718f7c8a78 : aco: fix waitcnt insertion on GFX10.3
b75427cc31f : panfrost: Implement EXT_multisampled_render_to_texture
2c47993b698 : panfrost: Add MSAA mode selection field
7973b6c1e00 : docs/features: Add GL_EXT_multisampled_render_to_texture
0c569e22d1d : radv: print warnings for famous RADV_PERFTEST options that no longer exist
65d23e7fb1e : radeon/vcn: Corrected vp9 ref associated data incase of target->codec is NULL
b98dd704894 : spirv: Propagate explicit layout only in types that need it
9a9b35a3bb4 : lima: Fix lima_screen_query_dmabuf_modifiers()
ee2c58dde46 : tu: Implement VK_EXT_conditional_rendering
f226b198f5b : tu: Reset has_tess after renderpass
06332ef60e8 : freedreno: Document draw predication packets
9e48e31fa54 : tu: Fix DST_INCOHERENT_FLUSH copy/paste error
95db96d75b4 : turnip: implement VK_EXT_4444_formats
036ff531439 : util/format: translate A4R4G4B4_UNORM and A4B4G4R4_UNORM vulkan formats
35f8f355f31 : turnip: rework extended formats to allow more extended formats
0b2478381f1 : ci: Actually upload trace artifacts to MinIO for baremetal
67b1163f9fb : turnip: add support for D32_SFLOAT_S8_UINT
a133f7d2885 : ci: Remove kernel module build that slipped in
76330374413 : ci: Download traces from MinIO in baremetal runs
d4ca45eca2a : ci: Upload traces' reference and actual images to MinIO
4816f6f8d88 : spirv: Do more complex unwrapping in get_nir_type
140a5492e04 : compiler/types: Add a struct_type_is_packed wrapper
66d8bbd8229 : freedreno: Fix "Offset of packed bitfield changed" warnings:
ba6cdb275c3 : turnip: delete tu_clear_sysmem_attachments_2d
9b6486bd3d9 : turnip: fix sysmem CmdClearAttachments 3D fallback breaking GMEM path flush
611f654fcf7 : nir/deref: Don't try to compare derefs containing casts
ee2f21b10dc : nir: Remove the old nir_opt_shrink_load.
d8c2f896dba : amd: Swap from nir_opt_shrink_load() to nir_opt_shrink_vectors().
023e6669cc1 : i965: Enable vector shrinking in the vec4 backend.
1c9906d5ff2 : nir: Add a pass to cut the trailing ends of vectors.
5afaec37413 : turnip: workaround for a630 d24_unorm_s8_uint fails
6fc52739bb4 : etnaviv: fix nir validation problem
caa107cb8db : freedreno/decode: move dependencies up a level
9c33c538981 : freedreno/registers: install gzip'd register database
62ebd342e67 : freedreno/registers: split header build into subdirs
e59b2412135 : freedreno/registers: add .gitignore
24f55eb6e80 : freedreno/rnn: rework RNN_DEF_PATH construction
bf425b7e513 : freedreno/rnn: also look for .xml.gz
8efdd388e03 : radv: Implement VK_EXT_4444_formats
3c2a1af660f : anv: Implement VK_EXT_4444_formats
b44139ef369 : vulkan: Update Vulkan XML and headers to 1.2.149
070fd2b66f9 : u_prim_restart: add inline function for getting restart index based on index size
1f24c54458c : iris: Zero the add-on clear color BO on import
a9560939e07 : ci: Build-test Panfrost tools
cd1c21f8e5b : zink: implement handling for VK_EXT_calibrated_timestamps
8930b196762 : zink: store valid timestamp bits onto zink_screen
3e6366be685 : zink: handle VK_EXT_vertex_attribute_divisor setup
99b44536bf2 : zink: clamp PIPE_SHADER_CAP_MAX_SHADER_BUFFERS to PIPE_MAX_SHADER_BUFFERS
01d6220cffb : zink: implement VK_EXT_robustness2
b2f475251ed : pan/mdg: Test for SSA before chasing addresses
b4de9e035ac : pan/mdg: Mask spills from texture write
26dd8f80453 : swr: Bump maximum 2D texture size to 16kx16k
99cf9108340 : mesa/st: Actually free the driver part of memory objects on destruction.
63bff6a9f89 : gallivm/nir: Lower uniforms to UBOs in llvm draw if the driver didn't request this already
b54afde3ad6 : android: freedreno: move a2xx disasm out of gallium
ca114e62735 : android: freedreno/common: add support for libfreedreno_common static
f065ec43aba : android: freedreno/ir3: fix include paths
711c30b764e : android: freedreno/registers: fix generated headers rules
32e0f7e0972 : anv: toggle on VK_EXT_extended_dynamic_state
b9a05447a19 : anv: dynamic vertex input binding stride and size support
e4590c07500 : anv: depth/stencil dynamic state support
f6fa4a80000 : anv: add support for dynamic primitive topology change
f426663f9c7 : anv: add support for dynamic viewport and scissor with count
9220598b367 : anv: add support for dynamic cull mode and winding order
c34d8ac26e0 : anv: handle dynamic viewport count
11f3fb9a4e2 : anv: consider dynamic state when creating pipeline
65de778e0b5 : anv: add new dynamic states
2260ce6d0c5 : anv: add VK_EXT_extended_dynamic_state but leave it disabled
a4181fcd422 : meson: fix `-D xlib-lease=auto` detection
c1476044b55 : egl: consistently use dri2_egl_display() helper macro
27eea627ef2 : freedreno/afuc: Fix PM4 enum parsing
a5daaed587c : freedreno/afuc: Add missing rnn_prepdb()
8d0e5e06266 : freedreno/cffdec: Stop open-coding enum parsing
73241ca53e8 : freedreno/rnn: Make rnn_decode_enum() respect variants
b67695d5973 : egl/haiku: drop overwritten preset of EGL version
9c6fa9421d5 : egl: const _eglDriver
81c0e2ab63d : egl: Allow software rendering for vgem/virtio_gpu in platform_device
eaf27eb512c : intel/tools: Test notification subregisters
ac7ecd205b2 : intel/tools: Simplify notification register handling
63181df09bc : intel/tools: Don't hardcode notification register
90c18ec8db8 : intel/tools: Manually set ARF register file/nr/subnr
af6d6f5c432 : intel/tools: Pass integers, not enums, to stride()
c883c482be2 : intel/compiler: Relax SENDS regioning assertions
363e5ef5a5d : intel/tools: Simplify dstregion
3d9c673c0f7 : intel/tools: Simplify immediate handling
59801f07e70 : intel/tools: Make writemask an integer
e115c499da2 : intel/tools: Make swizzle an integer
3e1602cc4fd : intel/tools: Simplify register type handling
2851c218e28 : intel/tools: Don't allow empty type specifier
6809b934113 : intel/tools: Remove stray newline
fdfbb1ed262 : intel/tools: Fix typos
2dec9092bee : pan/bit: Remove BI_SHIFT stub
aa989aed6d6 : pan/bit: Update f32->f16 convert test
cf8a8b764e5 : ci: Set date in LAVA DUTs from NTP servers
7f40db42a2d : docs: Explain how to set up a personal gitlab runner.
8e626879ddd : freedreno/a6xx: Fix CP_BIN_SIZE_ADDRESS name
6c11a7994dd : i965/i915: Add colorspace support to YUV sampling
d8fdb8dab46 : nir: Add colorspace support to YUV lowering pass
f7f31f02f50 : mesa: utils: fix check of option is not found
f3509c07663 : zink: add extension loading framework for spirv builder
a91011c9eca : pan/mdg: emit REGISTER_UNUSED on unused ALU src2
a2065917cc8 : mapi: Return NULL function pointers for GL_EXT_debug_marker
258165bed4d : egl: drop left-over function prototype
ed3f1e04c7d : egl: rename _eglMatchDriver() to _eglInitializeDisplay()
6d6b82a159c : egl: inline _eglMatchAndInitialize() and refactor _eglMatchDriver()
a77050c0345 : egl: fix _eglMatchDriver() return type
f91851e6159 : egl: drop unnecessary _eglGetDriver()
d24e3ea8cb2 : egl: replace _eglInitDriver() with a simple variable
3d4deb659e1 : pan/mdg: remove ins->br_compact and ins->branch_extended
8150c1d6320 : pan/mdg: defer branch packing
140185eb047 : pan/mdg: refactor emit_alu_bundle
0f0f9ee710f : pan/mdg: remove ins->alu
5299239c2ea : pan/mdg: externalize mir_pack_mod
1a4d165683a : pan/mdg: defer register packing
bea6a652db5 : pan/mdg: eliminate references to ins->load_store.op
92c808cd475 : pan/mdg: eliminate references to ins->texture.op
83592de7ad2 : pan/mdg: apply float outmods to textures
5011373e2b4 : pan/mdg: eliminate references to ins->alu.outmod
f34815c6bef : pan/mdg: fix comment
5f7e0185cd9 : pan/mdg: eliminate references to ins->alu.reg_mode
f4c89bf9bdf : pan/mdg: eliminate references to ins->alu.op
598527f2feb : pan/mdg: prepare effective_writemask()
b1b0ce04b3e : pan/mdg: fix src_type in instructions that need a implicit zero
75b1f3d39df : drm-shim: Return -EINVAL instead of abort()ing on unknown ioctls.
c77a414ec2d : u_prim_restart: handle indirect draws
a58081f97c1 : panfrost: Android build fixes 2020 week 31
75a68eee282 : aco: optimize swizzled SALU 8/16-bit conversions
80c135e6a6a : radv: fix build on Android 7 (v2)
e1b114868a1 : nir: Get rid of __[u]int64_to_fp32() and __fp32_to_[u]int64()
025988f8185 : intel: Set int64_options to ~0 when lowering 64b ops
936c58c8fcc : nir: Extend nir_lower_int64() to support i2f/f2i lowering
bfee35b45cc : nir: Stop passing an options arg to nir_lower_int64()
9e23925991a : freedreno: Initialize lower_int64_options to a proper value
f1f9fdb8a6a : aco: add GFX6/7 subdword lowering tests
000530ea686 : aco/tests: add tests for sub-dword swaps
54394a4d3b1 : ci: enable ACO tests
d488d0fd7ba : aco: add framework for testing isel and integration tests
bb7d7755f56 : aco: add a few tests for the assembler and optimizer
e6366f90943 : aco: add framework for unit testing
dd155aef440 : nir: Allow casts in nir_deref_instr_get[_const]_offset()
6a1382399cb : nir: Use a switch in build_deref_offset()/deref_instr_get_const_offset()
e933ac21cb3 : ci: Generate MinIO credentials within LAVA jobs
cb82274538b : ci/bare-metal: Capture the first devcoredump a job produces.
3120b4dcd30 : ci: Print URL to image diff when a trace replay fails
bea34a08534 : ci: Upload reference images for traces
cb19fe24d36 : intel/vec4: fix out of bounds read
56228b03937 : iris: quiet down static analyzers
c3a251f254e : mesa: quiet down static analyzers
0906d5d504e : mesa: fix out of bounds access in glGetFramebufferParameterivEXT
28f25853658 : util/format: initialize non-important components to 0
f13042ec7ea : util: fix possible buffer overflow in util_get_process_exec_path
59bb0ff945f : glsl: catch out of bounds access in the debug version
eac0ba7fc19 : util: fix possible fd leaks in os_socket_listen_abstract
62bfc700f74 : vulkan/util: add struct vk_pipeline_cache_header
b5558f2d2aa : freedreno/a6xx: fixup draw state earlier
82b419fefde : freedreno/a6xx: don't emit a bogus size for empty cb slots
ba9d502d246 : freedreno/ir3: add missing track_ubo_use()
d0e32e5f810 : egl/dri2: only take a dri2_dpy reference when binding a new context/surfaces
b9391c1d50b : freedreno/decode: cffdec warnings cleanup
20e703b7e62 : freedreno/rnn: headergen2 warnings cleanup
128cbcd3a7b : iris: Delete shader variants when deleting the API-facing shader
9a49d4c2db0 : aco: remove isel for GLSL-style barriers
cc3bc9493cf : radv: use scoped barriers
a8f8c02e7ef : ac/nir: implement scoped_barrier
6b99cf60640 : nir/load_store_vectorize: fix indentation
1a42e7dae94 : nir: Filter modes of scoped memory barrier in nir_opt_load_store_vectorize
5c5555a8627 : nir: Add a find_variable_with_[driver_]location helper
fc1363cc603 : nir/gl_nir_linker: Call add_vars_with_modes once for GL_PROGRAM_INPUT
789ec95dcd1 : nir/split_per_member_structs: Inline split_variables_in_list
d70fff99c5b : nir: Use a single list for all shader variables
473b0fc25dc : gallium/ttn: Use variable create/add helpers
a41a84d3620 : mesa/ptn: Use nir_variable_create
e5536e4a78e : aco: Use nir_foreach_variable_with_modes to walk SSBOs
a61be312e21 : panfrost: Use nir_foreach_variable_with_modes in pan_compile
94f0bae4de7 : panfrost/midgard: Make search_var take a nir_shader and mode
568022be753 : r600/sfn: Use nir_foreach_variable_with_modes in IO vectorization
cc51cec9c08 : r600/sfn/lower_tex: Get rid of the lower_sampler vector
929673077c6 : r600/sfn/lower_tess_io: Rework get_tcs_varying_offset
e4d812db10a : freedreno/ir3_cmdline: Rework i/o variable fixup
ce6e59b3d34 : lima/standalone: Rework i/o variable fixup
52dd84a12ec : freedreno/ir3_lower_tess: Rework var list helpers
77c41ce04bf : nir/gl_nir_linker: Use nir_foreach_variable_with_modes
c256cd900e7 : nir/lower_variable_initializers: Restrict the modes we lower
4d7e064623e : nir/split_per_member_structs: Use nir_variable_with_modes_safe
90cf4709d92 : nir/lower_uniforms_to_ubo: Use nir_foreach_variable_with_modes
d0d5ef61398 : nir/lower_two_sided_color: Use nir_variable_create
bb3994cfe7d : nir/io_to_vector: Use nir_foreach_variable_with_modes
0a77c674423 : nir/lower_io_to_temporaries: Use a separate list for new inputs
cd66005b23c : nir: Use a nir_shader and mode in lower_clip_cull_distance_arrays
d5d15c301e1 : nir/lower_amul: Add a variable mode check
3be0be7d545 : nir: Split nir_index_vars into two functions
86c93038148 : nir/split_vars: Add mode checks to list walks
2f6c263cc37 : st/nir: Rework fixup_varying_slots
4c3a30393d9 : nir/linking: Rework some internal helpers
caab46c1e93 : nir: Take a shader and variable mode in nir_assign_io_var_locations
964c1c4b877 : nir: Take a nir_shader and variable mode in assign_var_locations
6f6f7a34c5b : nir: Add and use a nir_variable_list_for_mode helper
e3e1c50067e : nir: Add a nir_foreach_gl_uniform_variable helper for GL linking
feb32f898c6 : nir: Add a nir_foreach_uniform_variable helper
92dcda5ce91 : nir: Add a nir_foreach_function_temp_variable helper
2956d53400f : nir: Add nir_foreach_shader_in/out_variable helpers
9bf85722220 : nir/dead_variables: Respect the modes passed to remove_dead_vars
5746af44460 : nir: Take a mode in remove_unused_io_vars
fd91744bd42 : docs: change "Fixes:" tag example to match git fixes output
aa89693c027 : freedreno/rnn: add schema validation
3169b8c645e : freedreno/rnn: schema updates for dynamic/irregular offsets
c5379471455 : freedreno/registers/mdp5: fix validation error
0586238036c : freedreno/rnn: fix use-group
14a7ca577f4 : freedreno/rnn: allow name to be optional in arrays
e801069c1e4 : freedreno/rnn: add "addvariant" to schema
b0e3ef5a250 : freedreno/rnn: describe copyright element in schema
09a3a2cfe9c : freedreno/registers/adreno_pm4: fix validation errors
c61ad1f542e : freedreno/registers/a4xx: fix validation error
17997d5c5a3 : freedreno/registers/a2xx: fix validation error
64f1122168f : freedreno/rnn: add variants/varset to domain
7b76e5f3a4d : freedreno/rnn: relax Hexadecimal to HexOrNumber
cb3ed4600e4 : freedreno/rnn: add radix/align
83bc96b555e : freedreno/rnn: add high/low/pos to registers
61ae65a73d4 : freedreno/rnn: add relaxed boolean type
e3958ef83a1 : freedreno/rnn: update schema for 'pos'
dfe9746be0d : freedreno/rnn: rename schema file
5a8d19ca141 : freedreno/rnn: add error helper
3a910839baf : freedreno/rnn: split out helper to find files
751af16e1d4 : freedreno/tools: check rnn parse status
6c8b921572a : ci: Build kernels and rootfs for x86 devices
5d0ba8b1834 : ci: Split building of libdrm to its own script
8a8afcbe403 : ci: Don't ship vk-build-programs after building dEQP
5262cd8be51 : ci: Fix URL for glslang
745540378c0 : ci: Print load stats after running dEQP
735ad2d2111 : ci: Always print status code of HTTP uploads in tracie
903a7d0f878 : freedreno: Add trace for CP_DRAW_INDIRECT_MULTI
85e43052352 : freedreno/cffdec: Handle CP_DRAW_INDIRECT_MULTI like other draws
4b940532fbd : freedreno/rnn: Support stripes in rnndec_decodereg
9a1924d55ad : tu: Dump CP_DRAW_INDIRECT_MULTI draw BO's
c7626ac8ba8 : bifrost: Fix packing of ADD_FEXP2_FAST
a618631f2dd : bifrost: Honor src swizzle in special math ops
a400c2ff226 : prevent multiply defined symbols
b11ebbe2f6a : amd: enable displayable DCC for everything newer than Navi1x
abed921ce71 : amd: add support for Navy Flounder
037b84df11a : amd: rename SIENNA -> SIENNA_CICHLID
ccfe9813fb8 : aco: create acq+rel barriers instead of acq/rel
3d9eb17d5d0 : aco: improve workgroup-scope and lower vmem/smem barriers
3af2b9e3de2 : aco: improve sync_info for TCS output stores
8a16498cc63 : aco: use storage_scratch
46c4b256239 : aco: enable value numbering of s_buffer_load_*
2adb337256f : nir,radv/aco: add and use pass to lower make available/visible barriers
7a614806134 : aco: consider intrinsic access in visit_{load,store}_image
cd392a10d05 : radv/aco,aco: use scoped barriers
d1f992f3c2d : aco: rework barriers and replace can_reorder
1bbb64f300f : aco: add missing add_to_hazard_query
1882b1e5a7d : bifrost: Add support for nir_op_iabs
1cdd161a302 : anv: fix descriptor set free
845a50ee252 : nine: fix incorrect calculation of layer count for 3D textures
d136fa17aca : panfrost: Allow PIPE_TEXTURE_1D_ARRAY textures
884718313c8 : i965: propagate error from gen_perf_begin_query to glBeginPerfQueryINTEL
627c01977c2 : iris: propagate error from gen_perf_begin_query to glBeginPerfQueryINTEL
0f9131d096e : freedreno/rnn: Return success when parsing addvariant
aa6fbdd2488 : freedreno/ci: add a2xx trace to CI job
18bc5a81a76 : freedreno: deduplicate a2xx disasm
f39afda1a7a : freedreno: move a2xx disasm out of gallium
f7bd3456d79 : freedreno: deduplicate a3xx+ disasm
6b379a4cb4b : freedreno: drop shader_t
bb98b71893f : freedreno/ir3: split out regmask
ddcee248adf : freedreno: add CI for envytools tools
b62e4a8e9e3 : freedreno/afuc: warnings cleanup
5125b4bc697 : freedreno/decode: warnings cleanup
cbbaafdf72c : freedreno/rnn: warnings cleanup
536f43cb96b : freedreno: slurp in afuc
1ea4ef0d3be : freedreno: slurp in decode tools
7c0bd8429f3 : freedreno: slurp in rnn
b721d336da9 : freedreno: slurp in rnndb
7de0842d428 : freedreno: make gen_header.py check parent directory
05b27832706 : radv: Fix host->host signalling with legacy timeline semaphores.
9746e84a7e5 : radv: cleanup locking around timeline waiting.
a0a70879c5b : bifrost: Add support for nir_op_imul
718d444e51a : bifrost: Add support for nir_op_uge
946ff9b4396 : bifrost: Add support for nir_op_ishl
539ea087368 : bifrost: Add support for nir_op_inot
12dd5455f43 : spirv: Handle most execution modes earlier
ef781880eb3 : bifrost: Add lowering for b2i32
1a168c90a01 : bifrost: Document d3d/gl comparison control bit
ec37c7126dc : bifrost: Emit "d3d" variant of comparison instructions
0ffefad7916 : bifrost: Lower x->bool conversions to != 0
8e8baecd6aa : tu: Enable resource dynamic indexing
8bc060ab81b : ir3: Fix incorrect src flags for samp_tex
e73a8a2b395 : ir3: Remove redundant samp_tex validation
3adc23f667b : ir3: Validate bindless samp_tex correctly
d542bfc3066 : tu: Fix descriptor update templates with input attachments
9ece61269d6 : turnip: fix SP_HS_UNKNOWN_A831 value for A650
e646e77e185 : turnip: use patchControlPoints for HS_INPUT_SIZE value
da49a453515 : turnip: move WFI out of draw state to fix a650 hangs
e5f4527f20d : freedreno/ir3: fix wrong local_primitive_id_start type
7cb4d4f24ec : vulkan/wsi: Convert usage of -1 to UINT32_MAX.
e1147caecb2 : vulkan/wsi/x11: report device-group present rectangles with prime.
af0bc710159 : radv: call radv_nir_lower_ycbcr_textures after first optimizations
fffc287d447 : radv: link with ld_args_build_id
d1677c8f8cd : v3d/compiler: request fragment shader clip lowering to be vulkan compatible.
71d5c192418 : v3d/compiler: handle compact varyings
17fd191eed5 : nir/lower_clip: make the pass compatible with Vulkan semantics
18fe130ec9e : radv: Fix uninitialized variable in renderpass.
e2e89fb137c : nir/lower_io: assert that offsets are used for shader_in
60915f87c73 : etnaviv: do register setup only once
7ee146aad49 : etnaviv: move shader_count to etna_compiler
5839a7d64a2 : etnaviv: introduce struct etna_compiler
9e596cc2c21 : tu: Enable vertex & fragment stores & atomics
f7f29a04b48 : tu: Detect invalid-for-binning renderpass dependencies
d6d75fcd915 : tu: Fix hangs for DS with no output
7ad962bf89f : tu: Fix empty blit scissor case
63cf8adb124 : spirv: Also copy over binding information for atomic counters
6cbdffd79ce : tu: Implement VK_KHR_draw_indirect_count
52ec35f5a63 : tu: Add missing wfi to tu6_emit_hw()
a0ca688a674 : tu: Integrate WFI/WAIT_FOR_ME/WAIT_MEM_WRITES with cache tracking
cd78a7a5ff5 : freedreno: Add INDIRECT_COUNT CP_DRAW_INDIRECT_MULTI variants
8da31ee15ff : freedreno: Clean up CP_DRAW_MULTI_INDIRECT definition
1747f9fdd07 : turnip: remove extra gmem alignment
8534f49bf93 : etnaviv: explicitly set nir_variable_mode
5b300bec9ad : radv: clean up remaining pipeline init functions
5575ce0a28e : radv: remove useless return value to radv_pipeline_scratch_init()
0721e2d1ab6 : radv: add radv_pipeline_init_shader_stages_state()
f3774ec9ac3 : radv: constify all radv_pipeline_generate_*() helpers
f32cb825159 : radv: assign pipeline gfx fields before PM4 emission
2a5fb87de2e : radv: clean up binning state initialization
08dd70465e6 : radv: clean up adjusting MSAA state if conservative rast is enabled
067b01c5e61 : radv: add radv_pipeline_generate_vgt_gs_out()
749d5134675 : radv: add radv_pipeline_init_input_assembly_state()
e31f8b96764 : radv: clean up tessellation state emission
9b691bfb6cf : radv: remove unnecessary radv_tessellation_state::lds_size
a1b237b9ef6 : radv: set LDS TCS size at shaders creation for GFX9+
cf89bdb9ba9 : radv: align the LDS size in calculate_tess_lds_size()
9c36ebf30e8 : radv: remove one unnecessary param to radv_generate_graphics_pipeline_key()
55f615660cb : radv: remove no-op si_multiwave_lds_size_workaround()
7f794137daa : radv: remove unnecessary radv_tessellation_state::num_patches
83f63ab2c2c : radv: clean up radv_compute_generate_pm4()
8bfd8277ccb : radv: reduce the number of allocated dwords for compute CS
62ec89759ab : radv: clean up PA_SC_CLIPRECT_RULE emission
09c4f76d913 : radv: clean up VGT_SHADER_STAGES_EN emission
62ffa837d34 : radv: emit PA_SC_LINE_CNTL as part of the rasterization state
934d6ac949f : radv: emit more invariant registers as part of the initial gfx state
847e0b83ba6 : radv: remove outdated TODO related to PA_SU_VTX_CNTL.PIX_CENTER
62af9df36c1 : radv: remove set but unused radv_pipeline::vertex_elements
76de1414c1e : radv: remove declared but unused radv_pipeline::is_dual_src
859687313be : bin/khronos-update: add workaround for python bug 9625
aa5c3911d67 : bin/khronos-update: add support for the SPIRV files
ccb91bc68c5 : bin/khronos-update: having a folder in include/ is not a requirement
de5130fea05 : v3d: Retry with the fallback scheduler when RA fails
1c8167da612 : v3d: Changed v3d_compile:failed to an enum
56846a2b682 : nir/schedule: Add an option for a fallback scheduling algorithm
08f1746fad7 : v3d: Mark scheduling dependency for prim id and first output
bafd2591771 : nir/schedule: Add a callback for backend-specific dependencies
260a8f759a7 : nir/schedule: Store a pointer to the options struct in scoreboard
7665398e6c4 : nir/scheduler: Move nir_scheduler to its own header
14a12b771d0 : spirv: Rework our handling of images and samplers
196db51fc27 : anv,turnip,radv,clover,glspirv: Run nir_copy_prop before nir_opt_deref
66c8628b65c : spirv: More heavily use vtn_ssa_value in function parameter handling
32ba23f8977 : spirv: Remove a dead case in function parameter handling
9e3213ad30f : spirv: Add a helper for getting the NIR type of a vtn_type
051f8d3d1cf : spirv: Give atomic counters their own variable mode
8a7932b0953 : spirv: Drop the sampled boolean from vtn_type
d0be2fed4ed : spirv: Add better checks for SSA value types
47ebb50cab3 : spirv: Hand-roll fewer vtn_ssa_value creations
085ade41255 : spirv: Simplify vtn_ssa_value creation
00af1128a9d : spirv/subgroups: Refactor to use vtn_push_ssa
ea246c39507 : spirv/subgroups: Stop incrementing w
c5fcd129ea1 : spirv/glsl450: Use vtn_push_ssa_value
7560ed279fd : spirv/alu: Use vtn_push_ssa_value
dbb4a24413d : spirv: Refactor vtn_push_ssa
8be9f2a4f69 : spirv: Use the new helpers in OpConvertUToPtr/PtrToU
37ab3234805 : spirv: Add a vtn_get_nir_ssa helper
e5b29b9040e : spirv/amd: Use vtn_push_nir_ssa
d8eb6f2499c : spirv: Add a vtn_push_nir_ssa helper
aaf1f342152 : spirv: Rename push_value_pointer to push_pointer
ac1e6d5a468 : spirv: Add a helpers for getting types of values
953b7a36032 : spirv: Use nir_bany/ball for OpAny/All
8dfee57bdc1 : spirv: Clean up OpSignBitSet
62c53ad20b7 : spirv: Fix indentation in vtn_handle_ptr
516fd78d627 : spirv: Drop the void *ptr from vtn_value
af81486a8cd : spirv: Simplify our handling of NonUniform
0d5cd1a5f41 : nir/vtn: Add support for 8 and 16 vector ball/bany
456edf0b302 : nir: Support 8 and 16 component vectors for reduceable intrinsics
d572f4dfd9c : nir: Support algebraic opts on vectors larger than 4
aa581fcc696 : nir: Support vec8/vec16 in nir_lower_bit_size
d35b54c7058 : freedreno: sync registers from envytools
1610c69f34d : tu: Enable VK_EXT_depth_clip_enable
1b3be07b5fa : aco: ensure readfirstlane subdword operands are always dword aligned
4c89bfc4ec0 : aco: prevent infinite recursion in RA for subdword variables
626081fe4bf : aco: don't split store data if it was already split into more elements
bd75e992330 : aco: ensure to not extract more components than have been fetched
6bc5ce7a91d : radv: Add timeline syncobj for timeline semaphores.
55d8022878f : radv: Add winsys functions for timeline syncobj.
66e598d0a6f : radv: Add winsys support for submitting timeline syncobj.
fb6b38d7800 : radv: Add thread for timeline syncobj submission.
fa97061a823 : radv/winsys: Add binary syncobj ABI changes for timeline semaphores.
fb5237910b2 : amd: Add detection of timeline semaphore support.
ce4064fe2fe : nir/ lower_int_to_float: Handle umax and umin
589d8665f01 : ci: Use half as many parallel softpipe / virgl test jobs
d9693c6620d : ci: Do not mark container / pages jobs as interruptible
e74933e8ab3 : ci: Use FDO_CI_CONCURRENT in run-shader-db.sh as well
429ec827d4a : ci: Namespace trace artifacts to the job number
772ed657a27 : nir_ allow nir_lower_clip_halfz to run in tess eval shader
09ecfd95ee1 : nir: allow lower_psiz_mov to run in tessellation stages
fced3c43e7a : Revert "llvmpipe: Use the default behavior of ALLOW_MAPPED_BUFFERS."
be6c53bb9d3 : llvmpipe/ms: fix sign extension bug in rasterizer.
4d73988f6fe : intel/ir/gen12+: Work around FS performance regressions due to SIMD32 discard divergence.
45d159cb410 : glx: Fix build and warnings with -Dglx=dri -Dglx-direct=false
ba22f014f9d : softpipe: Enable PIPE_CAP_TGSI_ANY_REG_AS_ADDRESS;
8e61fd92d4a : softpipe: Enable PIPE_CAP_TGSI_TEXCOORD.
259a03b4f0b : softpipe: Add support for reporting shader-db output.
991def0edc8 : softpipe: Convert to comma-separated SOFTPIPE_DEBUG for debug options.
86cfb62b87e : softpipe: Refactor pipe_shader_state setup.
e67da8d25fa : llvmpipe: enable robust buffer access + GL 4.3, GLES 3.2 and robust buffer access behaviour
6d3cefe727f : llvmpipe: add device reset query context hook.
3cb3d17312f : glx/drisw: add robustness support
80f7b58d901 : drisw: add robustness extension support.
12c06a0deb6 : llvmpipe/draw: handle constant buffer limits and robustness (v1.1)
f0c3a258003 : llvmpipe: enable EXT_texture_shadow_lod
c30824adc07 : nir/lower_io: Add support for global scratch addressing
4815ae51d72 : nir/lower_io: Use b2b for shader and function temporaries
3a2975db987 : nir/lower_io: Choose to set access based on intrinsic metadata
c475e29be4f : nir: Allow for system values with variable numbers of destination components
0338db5e6b0 : docs/releasing: improve wording
ae2d0457679 : bin/gen_release_notes: automatically commit release notes
5f649be7b58 : post_version.py: fix relnotes links
6c4ad627230 : post_version.py: update the files in the current worktree, not the one with the script that we run
a28a0898149 : post_version.py: stop using non-existent functions and fix commit message
f5353e01f95 : post_version.py: drop incorrect conf.py changes
24e118f6957 : post_version.py: don't generate relnotes twice
04e38eb2e76 : docs: update calendar and link releases notes for 20.1.4
8a44983c126 : docs: add release notes for 20.1.4
b6b100ccaee : gitlab-ci: Test AMD's Raven with traces
eb7642c53d0 : i915: Remove a bunch of default handling of pipe caps.
e35d3d26b17 : svga: Remove a bunch of default handling of pipe caps.
c32f723a1a6 : swr: Use the default behavior of ALLOW_MAPPED_BUFFERS.
39598a16e98 : swr: Remove a bunch of default handling of pipe caps.
e2ffd2110e9 : virgl: Remove a bunch of default handling of pipe caps.
e5554e32c0f : softpipe: Use the default behavior of ALLOW_MAPPED_BUFFERS.
855f3ff4187 : softpipe: Remove a bunch of default handling of pipe caps.
6ec49066498 : llvmpipe: Use the default behavior of ALLOW_MAPPED_BUFFERS.
ae919b2561f : llvmpipe: Remove a bunch of default handling of pipe caps.
292882f6bc4 : ci: Fix the overwriting of traces.yml for baremetal
262731be430 : ci: Update checksums for freedreno traces.
46646123ab0 : radeon/vcn: increase render_pic_list size
89d2dac5548 : radeonsi: enable preemption if the kernel enabled it
9e2113c6dc1 : radeonsi: set up IBs for preemption
b8892bc8182 : radeonsi: don't restore states at the beginning of IBs if they're shadowed
95c9048591c : radeonsi: add debug code for register shadowing
8af0f91fd37 : radeonsi: add reg shadowing codepaths to GS and tess ring setup
69014d8c94f : radeonsi: implement CP register shadowing
b84dbd29369 : radeonsi: reorder code in update_gs_ring_buffers and init_tess_factor_ring
babd87f2e08 : radeonsi: make cs_preamble_state optional
7a6af4c5edb : winsys/amdgpu: make amdgpu_bo_unmap non-static
5a5467ccc80 : ac: add tables for CP register shadowing
dc3dade4750 : ac: add helper ac_get_register_name
976edae839a : radeonsi: sort registers in si_init_cs_preamble_state according to GPU gen
88fe9dea7a2 : radeonsi: sort registers in si_emit_initial_compute_regs according to GPU gen
1c6eca23fdd : radeonsi/gfx10: set the correct value for OFFCHIP_BUFFERING
d244a25c072 : radeonsi: add missing initialization of registers
fd20e986249 : docs: add some very basic documentation about zink
202592a3989 : radv/winsys: be more robust when a CS failed during recording
f82eb7af877 : radv/winsys: return a Vulkan error code when binding virtual buffers/images
4b58e35a2a8 : radv/winsys: remove useless check when binding virtual buffers/images
f0112fa13cc : radv/winsys: check more allocation failures
7a61e31d7b2 : radv: add missing return values check for some winsys calls
348e8b5618c : nir/tests: Add tests for opt_if_simplification
6f94b3da111 : nir/opt_if: Fix opt_if_simplification when else branch has jump
3f783a3c507 : zink: omit Lod image operand in ntv when not using an image texture dim
0ef5e19874b : zink: add some asserts for building access chains in ntv
2af22051c09 : zink: handle texelFetchOffset with offsets
6587f41e115 : zink: use helper function to handle uvec/bvec types
7015d2c249e : aco: fix scratch loads which cross element_size boundaries
c33e8d7d522 : mesa/program: fix shadow property for samplers
4b04800efae : ci: Disable trace testing on Mali T760
6c1108d25b4 : radv: advertise VK_EXT_shader_atomic_float
b8517e5ef9b : ac/nir: add support for nir_intrinsic_shared_atomic_fadd
7615f2d6900 : aco: add support for nir_intrinsic_shared_atomic_fadd
97482c6f929 : ci: Test with more traces
87e0b2c1c24 : ci: Prefix tracie artifacts with the device name
ed5374ff508 : ci: Use smaller glxgears trace
dfe394bac42 : ci: Upload images of failed replays to MinIO
7dc4fe6fb40 : nvc0: add documentation for nve4+ (Kepler) COPY class
203d565b195 : nvc0: fix macro define for NVE4_COPY()
3a4024e7766 : anv: properly handle fence import of sync_fd = -1
323d5bbfd9a : meson: Add mising git_sha1.h dependency.
12b99d25810 : aco: fix includes in aco_ir.cpp
8fff8afb134 : turnip: disable tiling for NV12/IYUV formats
b559d26c74a : freedreno/ir3: Fix SSBO size for bindless SSBO's
c11c4d8d4c1 : aco: fix copy of uninitialized boolean
40b65a86a45 : radv: fix invalid conversion warnings in vk_format.h
fcd8f691138 : aco: print ACO IR before scheduling instead of after
bf4b377b9b9 : aco: make validate() usable in tests
e75946cfefc : aco: move some setup code into helpers
2907faee7a3 : egl/dri2: try to bind old context if bindContext failed
8b0b6f907d7 : dri2: do not conflate unbind and bindContext() failure
6b12999ef7c : dri2: dri2_make_current() fold multiple if blocks
29c39aeaabc : aco: use nir_addition_might_overflow to combine additions into SMEM
72ac3f60261 : nir: add nir_unsigned_upper_bound and nir_addition_might_overflow
2694a34aa2c : aco: add NUW flag
3a4847179b9 : aco: allow overflow for some SMEM instructions
d169f09e378 : aco: be more careful combining additions that could wrap into loads/stores
4d0e06257a7 : gitlab-ci/traces: updated paths and checksums for POLARIS10 traces
f1e67aa08a1 : gitlab-ci: get the last frame from a gfxr trace using gfxrecon-info
d15e1226cce : gitlab-ci: build gfxreconstruct from the "dev" branch
bb5b136b452 : freedreno: Use common guardband helper
c9c848dedea : tu: Use common guardband helper
19895dde909 : freedreno: Add a helper for computing guardband sizes
86a65977140 : panfrost: Remove unused batch_fence->ctx
f18e5371cf0 : panfrost: Remove unused batch_fence->signaled
64d6f56ad26 : panfrost: Allocate syncobjs in panfrost_flush
85a2216fe4f : panfrost: Skip specifying in_syncs
e5ef5a381e8 : panfrost: Remove wait parameter to flush_all_batches
0c4db886b63 : panfrost: Avoid wait=true flushing all batches
04ea4f1ce47 : aco: implement b2i8/b2i16
3a7cd7bd65d : nv50/ir: initialize persampleInvocation to false
618b3555045 : nv50/ir/tgsi: silence warning about unhandled GS_INPUT_PRIM property
6ced98c94e2 : radv: disable CPU caching for the upload BO to reduce fetch latency
b3eae4e0376 : radv: do not perform read-modify-write with the upload BO
d9072a113b2 : radv: replace discard with demote for Quantic Dream games
51bc11abc20 : aco: always set FI on GFX10
8b3452a5566 : ci: Set XDG_CACHE_HOME to tmpfs for bare-metal runners to avoid NFS.
b2cd6a0b156 : gitlab-ci: Fix needs: of the arm64 LAVA test jobs
a1947f059fc : gitlab-ci: Upload tracie artifacts to MinIO
20507f8b17f : gitlab-ci: Download traces from MinIO
087be7e3220 : gitlab-ci: Replay traces on lava devices
576c53dadf3 : iris: Fix CCS check in iris_texture_subdata().
0868638aed0 : nir/lower_int64: lower 64-bit amul
4d44848c470 : anv: Advertise support for VK_EXT_shader_atomic_float
675d7b19a9a : intel/fs: Use the correct logical op for global float atomics
84086b620ee : spirv: Add support for SPV_EXT_shader_atomic_float
2a568c595be : spirv: Update headers and grammar json
cc03448008b : egl: inline _EGLAPI into _EGLDriver
7b7917a4241 : radeonsi: Inhibit clock-gating for perf counters.
794ba3efd7e : amd/registers: add RLC_PERFMON_CLK_CNTL for pre-GFX10
36e6ac65c51 : anv: Advertise VK_EXT_image_robustness
d973e50f699 : freedreno/ir3: Add missing ld_args_build_id to the ir3_delay unit test.
3688da2192e : radv: advertise VK_EXT_image_robustness
096adbe369a : ci: bare-metal: use nginx to get results from DUT
101400d4495 : mesa: change error code of *TextureSubImage* for incorreect target
af92348b1cd : freedreno/ir3: Fix disasm of register offsets in ldp/stp.
d6d8dc133e0 : freedreno/ir3: Refactor cat6 general dst printing.
62dcf754321 : freedreno/ir3: Add a bunch more tests for cat6 opcodes.
ed3338f581e : freedreno/ir3: Add a note about the instructions in the disasm test.
4ab3a219cc1 : vulkan: Update Vulkan XML and headers to 1.2.148
fd24a959956 : ci: Use FDO_CI_CONCURRENT as our -j flags when present in the runner env.
5f79e4e69af : nir/algebraic: fold some nested bcsel
27244662f25 : nir/algebraic: propagate b2i out of ior/iand
baee5a98122 : nir/algebraic: add distributive rules for ior/iand
70d3efeb88c : nir/algebraic: optimize (a < 0.0) ? -a : a -> fabs(a)
9d22c5ed718 : nir/algebraic: optimize fmul(x, bcsel(c, -1.0, 1.0)) -> bcsel(c, -x, x)
56ec814b567 : nir/algebraic: add some more unop + bcsel optimizations
2fca183910d : nir/algebraic: add optimizations for fsign/isign
8e1b75b3309 : nir/algebraic: optimize iand/ior of (n)eq zero
e4281dbecc6 : nir: also move b2i in case of nir_move_copies
de0ebaf09d4 : nir/algebraic: optimize bcsel(a, 0, 1) to b2i
e764192f401 : pan/mdg: Use the blend RT for blend shader framebuffer fetches
3ec252a3b29 : panfrost: 8x MRT support
978f963ea43 : panfrost: Use more tilebuffer sizes
c1d3d39e971 : panfrost: Fake RGTC support
fac813dc61e : spirv: don't split memory barriers
28c227c7ca3 : radv/winsys: always allow GTT placements on APUs
d1bba2eee79 : radv: disable CPU caching for IBS to reduce fetch latency
d2a3ca289f5 : radeonsi: adjust epitch for PIPE_FORMAT_R8G8_R8B8_UNORM
87ecfdfbf0a : ac/surface: adapt surf_size when modifying surf_pitch
1fa36c1d3d6 : d600/sfn: write stream outputs to correct mem ring
21d296a4817 : r600/sfn: Make the pin_to_channel generic
3ea847e6d1a : r600/sfn: Only use sample mask if the according shader key is set
c91979c6344 : r600: Add shader key item to identify when the sample mask should be used
05df4bfbcab : r600/sfn: Fix default z swizzle for GDS instructions
2779aa360ed : r600/sfn: Fix Ring output swizzle masks
c18b1c6df51 : r600/sfn: Add a forced output swizzle for depth write
d31ef0b7a4b : r600/sfn: correct handling of loading vec4 with fetching constants
aca99e6fc9d : r600/sfn: Add option to get a temp value for a specific channel
258618815b4 : r600/sfn: emit texture instructions in one block
deccf022464 : r600/sfn: Pipe through requesting a register at a given channel
55cc7129918 : r600/sfn: lower rotate ALU ops
4708ccbf918 : ci/llvmpipe: reenable gpu shader5 tests
41c7bb6ec04 : llvmpipe: add framebuffer fetching support (v1.1)
0e0b6d477b9 : llvmpipe/cs: respect render condition
912ad091125 : freedreno/ir3/ra: fix array conflicts for split/merged
b1465c382b5 : freedreno/ir3/ra: assign vreg names to all array elements
6317f7d574a : freedreno/ir3/ra: debug msgs tweak
c2d94aa365d : freedreno/ir3: fix half-reg array stores
5be171b8886 : freedreno/ir3: set array precision on creation
0472ca2aa5c : freedreno/ir3/parser: half-precision relative regs
79b0651c245 : freedreno: whitespace fix
835201dd76f : freedreno: small comment re-word
2b343238a1f : zink: free all ntv allocations after creating shader module
adc4f3896ae : zink: free pipeline cache during program destroy
1ff2d195b04 : zink: destroy descriptor pools on context destroy
7116decfce3 : zink: destroy gfx program when a shader is freed
9e9c8e2f794 : android: panfrost/encoder: add libmesa_nir static dependency
0ef168d5130 : panfrost: Fix calls to panfrost_flush_batches_accessing_bo
858cc13eb28 : panfrost: Make panfrost_bo_wait take a wait_readers bool
5b380483476 : freedreno/ir3: Add unit tests for derivatives disasm.
3d7d5d220b5 : freedreno/ir3: Fix duplicated fine derivatives instructions.
862d85a63ff : amd/addrlib: Clean up unused colorFlags argument
a37aeb128d5 : amd/common: Cache intra-tile addresses for retile map.
f302ef3853b : aco: use s_waitcnt_depctr to mitigate VMEMtoScalarWriteHazard
bcf94bb933e : aco: properly recognize that s_waitcnt mitigates VMEMtoScalarWriteHazard
33f33bb7d69 : meson: Enable GCing of functions and data from compilation units by default.
610af7e1acc : panfrost: Enable FP16 by default
e5169b1ca1a : gitlab-ci: re-enable all a630 jobs
4080f8bf2b0 : freedreno/a2xx: Fix compiler warning in disasm.
cf55abe750f : gitlab-ci: Re-add kernels for bare-metal
2aa507f87a6 : nir: Set the alignment for SSBO lowering
d735f075a6a : intel/perf: Move perf query register programming to static tables.
d4e56930c25 : intel/perf: Fix unused var warning in release builds.
afe07c7fa7c : intel: Fix release-build warnings about sf_entry_size.
086f7609749 : zink: use ralloc for spirv_builder as well
810bf7d32b3 : zink: pass mem_ctx to ralloc_size-call
35beb938fc5 : zink: use ralloc for plain malloc-calls
12b324b30c5 : zink: use ralloc in nir-to-spirv
56d9bcdded8 : radv: enable more float_controls features
23631ddd4db : aco: set tcs_in_out_eq=false if float controls of VS and TCS stages differ
b36950ad2c0 : aco: fix nir_op_f2f16_rtne with non-default rounding modes
d14f4faa137 : aco: flush denormals before fp16 fabs/fneg if needed
305cffa22b3 : aco: use s_round_mode/s_denorm_mode
ca44c009b5e : panfrost: Set depth_enabled when stencil is enabled
2b796c76852 : radv: return better Vulkan error codes when VkQueueSubmit() fails
1829bdd0da7 : radv: improve the error messages when a CS submission failed
93047f68888 : radv: remove one useless goto in radv_queue_submit_deferred()
01147481f90 : panfrost: Report TEXTURE_BUFFER_OBJECTS cap when gl3 flag set
4e986568b8b : nir: Fix lower_two_sided_color when the face is an input
314ba5e1745 : nir: Add a face_sysval argument to nir_lower_two_sided_color
2a6db94b05c : panfrost: Do per-sample shading when outputs are read
c20d166b4ec : pan/mdg: Do per-sample framebuffer loads
25747cea67f : panfrost: Rename lower_store to is_blend in pan_lower_framebuffer
4a8ad1e08f9 : pan/mdg: Don't disassemble blit shaders
3f8656401b6 : gitlab-ci: Only trigger test-docs job automatically for MRs
575ab303a80 : virgl: set PIPE_CAP_BLEND_EQUATION_ADVANCED
a0f42b89a15 : virgl: Encode barrier for blend_equation_advanced
a026364b55e : virgl: Use alpha_src_factor to store blend_equation_advenced value
0ee1a67f3c8 : glsl_to_ir: do lower_blend_equation if PIPE_CAP_FBFETCH
d0df56ccd18 : st: expose KHR_blend_equation_advanced if PIPE_CAP_BLEND_EQUATION_ADVANCED
377731ec1bb : gallium: Add PIPE_CAP_BLEND_EQUATION_ADVANCED
57174c91023 : virgl: Reserved last caps of capability_bits
4f8fc0f0665 : glsl_to_tgsi: Set TGSI_PROPERTY_FS_BLEND_EQUATION_ADVANCED
b3a3f7cca23 : gallium: add TGSI_PROPERTY_FS_BLEND_EQUATION_ADVANCED
30f4ccff5bd : mesa: treat Color._AdvancedBlendMode as enum
6ffa0e92549 : mesa: do not use bitfields for advanced-blend state
c36aac542a3 : st/mesa: fix st_CopyPixels without support for stencil exports
e7fd1ce9a24 : nvc0_2d: Document SET_PIXELS_FROM_MEMORY_CORRAL_SIZE from rnndb
bc69e734153 : nv50_2d,nvc0_2d: Document SET_PIXELS_FROM_MEMORY_SAFE_OVERLAP from rnndb
912345840bb : docs/features: Mark trivial missed feature
e0ef5a5cba7 : egl: mark the rest of the callbacks as mandatory or optional
4dc322c4c67 : egl: drop now empty egl_dri2_fallbacks.h
bc38fe8425f : egl: inline fallback for get_sync_values
2e3eb0c90b7 : egl: inline fallback for create_wayland_buffer_from_image
c5fb1fbc9b9 : egl: inline fallback for query_buffer_age
90000b0264d : egl: inline fallback for copy_buffers
2d5f12ae3a6 : egl: inline fallback for post_sub_buffer
1ba5075a7e4 : egl: inline fallback for swap_buffers_region
7d5a13ebf31 : egl: inline fallback for swap_buffers_with_damage
b501ece6f60 : egl: drop unused fallback function
43e2d80849c : egl: inline fallback for create_pbuffer_surface
179e442f7a4 : egl: inline fallback for create_pixmap_surface
81124d845e5 : driconf: allowlist/denylist
01d60d3d754 : pan/decode: Open the dump file later
4dcbad476eb : gitlab-ci: Run all of GLES3 tests for Panfrost
4e8d7ad8b09 : radv: split fence into two parts as enum+union.
56395a8b6d6 : radv: optimize creating signaled syncobj with amdgpu_cs_create_syncobj2()
3b7cd734e8a : radv: fix the error code when allocating a fresh imported syncobj fails
dd795ee1df4 : radv: fix the error code when exporting a semaphore/fence fails
8aa9d0acb8c : radv: fix destroying the syncobj when exporting a fence FD
b5a48a948ac : tu: Enable VK_EXT_shader_stencil_export
aeca92ed798 : ir3: Handle gl_FragStencilRefARB
981608ad04c : freedreno/a6xx: Add stencilref register info
40b99bb79e1 : panfrost: Revert "Disable frame throttling"
19da8121d6a : panfrost: Enable Chromium
96fa8d70bc1 : panfrost: Report CAPs more honestly
afa4b32019a : panfrost: Fix faults with RASTERIZER_DISCARD
6c6a8b2f071 : panfrost: Honour cso->compare_mode
9addb82148c : panfrost: Avoid integer underflow in rt_count_1
77bb19eebd1 : panfrost: Abort on unsupported blit
cce3d925d24 : panfrost: Implement Z32F_S8 blits
6ffebfbff8a : panfrost: Fix sRGB clear colour packing
721b5c6eef6 : panfrost: Set PIPE_CAP_MIXED_COLORBUFFER_FORMATS
a0003c329a0 : panfrost: Overhaul tilebuffer allocations
3d13870ee2c : panfrost: Call util_blitter_save_fragment_constant_buffer_slot
e16f59c3162 : llvmpipe: fix position offset interpolation
87e27543fe9 : llvmpipe: fix stencil only formats.
045711dc1c0 : radeonsi: use PIPE_FORMAT_P010 for 10-bit VP9 decoding
b85ef043245 : aco: add add_interference() helper
2c7554fe012 : aco: use unordered_set for spill id interferences
47d7e1e6628 : aco: rewrite graph coloring in spiller
5a941f4d6dc : aco: fix underestimated pressure in spiller when a phi has a killed def
293f251871b : panfrost: Use Midgard-specific reloads
f611af35948 : st/mesa: use fragment shader to copy stencil buffer
3af0711c402 : mesa/main: use p_atomic_inc_return instead of locking
a0f84396913 : st/mesa: fix corrupted texture levels, when adding more levels than expected
b8c0196116d : gallium/util: do not use _MTX_INITIALIZER_NP on Windows
485ea7d711f : radv/winsys: pass the buffer list via the CS ioctl for less CPU overhead
40bea60dcf9 : radv/winsys: replace alloca() by malloc() everywhere
97f8ec321b7 : v3d/compiler: Lower geometry output store base into offset src
081691b5ae2 : radeonsi: prevent a gfx10_ngg_calculate_subgroup_info failure for TES+NGG GS
5714cd34333 : ci: bump piglit checkout for dsa tests
854dbea5671 : mesa: change dsa texture error codes for GL 4.6
34a03109b8e : panfrost: Extract panfrost_batch_reserve_framebuffer
5d0d8faaa64 : panfrost: Track surfaces drawn per-batch
64734c0947e : panfrost: Set zs_samples as necessary
8225604fd52 : panfrost: Handle per-sample shading
080b751d4ac : panfrost: Add rectangle subtraction algorithm
e061bf004b5 : panfrost: Identify zs_samples field
6088891ef79 : panfrost: Include sample count in payload estimates
5c65a27adc6 : panfrost: Add MALI_PER_SAMPLE bit
adacf1f5117 : panfrost: Expose panfrost_get_blend_shader
528e132d4f7 : panfrost: Force Z/S writeback
da2eed36f3c : pan/mdg: Implement gl_SampleID
b2749c141d5 : pan/mdg: Identify per-sample interpolation mode
59308a3a648 : pan/mdg: Bump compiler RT maximum
29849aca0fe : Android: Fixes for Q and R
2adb13f187f : llvmpipe/format: fix snorm conversion
75e01d01a53 : gallivm/sample: always square rho before fast log2
a9c94861063 : nv50_2d: regenerate envytools-based rnndb headers
0859dcb57c1 : radv: destroy the base object if VkCreateInstance() failed
50fdefc025a : radv: destroy the base object if VkAllocateCommandBuffers() failed
e5f2bf36972 : radv: destroy the base object if VkCreateFence() failed
d25764d9104 : radv: destroy the base object if VkCreateSemaphore() failed
ce7a7aeeccf : radv: destroy the base object if VkCreateEvent() failed
8ef52974cdb : radv: destroy the base object if VkCreateBuffer() failed
852316494cf : radv: destroy the base object if VkCreateImage() failed
2e5968023f7 : radv: destroy the base object if VkCreateRenderPass*() failed
0eec81d0192 : radv: destroy the base object if VkCreateQueryPool() failed
25baceafd3d : mesa/st: release debug_output after destroying the context
7f0b6a5df8e : mesa: add bool param to _mesa_free_context_data
e6f7b4312f5 : mesa: rename _mesa_free_errors_data
cbdb87c678c : gitlab-ci: Fix "triggered by Marge for a merge request" rule
559b26b7ee0 : intel/ehl: Add new PCI-IDs
7cb2ace4657 : intel/ehl: Rename gen_device_info struct
13c70931f59 : intel/ehl: Use macro GEN11_LP_FEATURES in device info
e08ec89a195 : intel/ehl: Use GEN11_URB_MIN_MAX_ENTRIES in device info
787c1ed2096 : panfrost: Dual source blend support
334dab05765 : pan/mdg: Skip z/s combining for dual-source writes
85954ecfefd : pan/mdg: Dual source blend input/writeout support
0ff6263534a : pan/mdg: Add a nir pass to reorder store_output intrinsics
58c0e1d0056 : gallium: Dual source support in blend_factor_to_shader
bedd4b44de3 : compiler: Add dual-source factors to blend_factor
7f9039f0a89 : freedreno/ir3: DCE unused arrays
2e4bab84fb6 : freedreno/a6xx: don't enable early-z/lrz if no z-test
37e0e0791f2 : freedreno/ir3/ra: be better at failing
afadaaef399 : freedreno/a6xx: bail instead of crash for compile fails
b3ca55f5aaa : freedreno/ir3: make compile fails more visible
788792fc466 : freedreno/ir3: add missing VS driver params
5e9cd64f70a : zink: enable tgsi texcoord pipe cap
05362b075fd : nouveau: expose HMM
212f1ab40ea : nvc0: support PIPE_CAP_RESOURCE_FROM_USER_MEMORY_COMPUTE_ONLY
c0f7f833eb9 : gallium: add PIPE_CAP_RESOURCE_FROM_USER_MEMORY_COMPUTE_ONLY
08ceba943d2 : nouveau: enable HMM
1f37662c093 : ci: bump libdrm to 2.4.102
96606552da1 : ci: need to install wget in order to download libdrm
0e90b3d0c4e : nir: Support load/store of temps as scratch in nir_lower_explicit_io
99aaf0ec181 : nir: When nir_lower_vars_to_explicit_types is run on temps, update scratch_size
bf138c1fd43 : nir_lower_io: Add addr_format_is_offset helper
d00487dd426 : freedreno/regs: update a6xx PC regs
2e32a20f7c7 : freedreno/regs: update a6xx VPC regs
e883aa25852 : freedreno/regs: update a6xx RB regs
a5c668518ad : freedreno/regs: update a6xx GRAS registers
be33d5859ea : gitlab-ci: re-enable arm64_a630_vk
f37f1a1a645 : turnip: remove use of tu_cs_entry for draw states
7f24a69acee : turnip: fix inconsistencies with tu6_load_state_size
bf997ca3065 : turnip: emit compute pipeline directly in CmdBindPipeline
dce6cb11961 : turnip: use DIRTY SDS bit to avoid making copies of pipeline load state ib
2e488305d65 : zink: try to handle multisampled null buffers
1ee598cfed3 : zink: handle empty attachments
6493d29f211 : pan/mdg: Fix non-debug compiliation
89caa485f15 : Revert https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4580
460300ed592 : nouveau: expose HMM
efa847dbc9d : nvc0: support PIPE_CAP_RESOURCE_FROM_USER_MEMORY_COMPUTE_ONLY
dd2cc5bc444 : gallium: add PIPE_CAP_RESOURCE_FROM_USER_MEMORY_COMPUTE_ONLY
f67cd0bbd97 : nouveau: enable HMM
6f4a6ed0e0b : ci: bump libdrm to 2.4.102
e1e7584bde7 : zink: block resolve blits for depth/stencil buffers
582669f07e7 : zink: block vkCmdBlitImage usage for multi sampled blits
ab78831baa6 : zink: try copy_region hook for blits where we can't do a regular blit or resolve
34fe561895b : mesa/main: use call_once instead of open-coding
0a4aa612ba2 : mesa/main: factor out one-time-init into a helper
38e3cbb6391 : gv100/ir: set ftz bit on floating point operations
f95637f01a7 : meson: fix android vulkan build
3ed104b2aa1 : gitlab-ci: Drop dependencies:
aa2457fc130 : gitlab-ci: Remove indirect dependencies from needs:
bf1376aba0e : tu: Don't invalidate irrelevant state when changing pipeline
a16136796ff : freedreno/a6xx: Add some documentation for shared consts
e1fa740c4c1 : freedreno/a6xx: Rename and document HLSQ_UPDATE_CNTL
dad042b15a9 : clover: implements clEnqueueFillBuffer
fea109d40ff : clover: add more cl_mem_object_type to pipe_texture_target mapping
ac642d8e6d4 : radv: add the custom border color BO to the list of buffers
684cfca7489 : freedreno/registers: Rename SP_2D_SRC_FORMAT
d5c82c3c5f2 : freedreno/a6xx: Split clear and blit texture into different functions
f383b2c18ac : freedreno/a6xx: Don't take pipe_blit_info in emit_blit_dst
3158b8ba0ab : freedreno/a6xx: Program RB_UNKNOWN_8C01 in setup helper
3ee89e6d03b : freedreno/a6xx: Move CP_SET_MARKER to setup helper
3961fb7e28b : freedreno/a6xx: Move REG_A6XX_SP_2D_SRC_FORMAT programming to helper
03ad130bc9c : freedreno/a6xx: Program A6XX_SP_2D_SRC_FORMAT_COLOR_FORMAT based on dst format
5c3c0c5c7b4 : freedreno/a6xx: Make blit_control helper a little more helpful
77d4aa76876 : freedreno/a6xx: Enable FMT6_10_10_10_2_UNORM blitting
1a58596258b : freedreno/a6xx: Separate stencil sysmem clear fix
ab61393bc75 : freedreno/a6xx: Don't emit src state when clearing
416513d915b : freedreno/a6xx: Consolidate computing blit_cntl
b36c675858f : freedreno/a6xx: Program SP_2D_SRC_FORMAT outside blit loop
556cd8f3e18 : freedreno/a6xx: Set src and dst rects outside blit loop
25bfc3b0494 : freedreno/a6xx: Don't set unknown bit when tiling differs
def7e7426de : freedreno/a6xx: Split out src and dst setup helpers for blit
bf0cf4c181f : freedreno/a6xx: Move fd6_ifmt into fd6_blitter.c
094b68fa728 : freedreno/a6xx: Don't blit with R2D_RAW
53e36cf062f : turnip: drop GS clear path
a1a80c38ea2 : turnip: clean up primitive output state
7748afbb1ed : freedreno/regs: update primitive output related registers
5c1afd1ce43 : freedreno/ir3: Fix uninit var warning.
afb3f21c9f1 : freedreno/ir3_cmdline: Fix an uninit var warning.
d941c6b74fe : turnip: implement VK_EXT_private_data
5d3fdbc52bf : turnip: Use the common base object type and struct.
cd85315dcb0 : tu: Fix wrong copies of sampler descriptor.
3a153137f4c : vulkan: Adds helpers for vk_object (de)alloation and (de)initialization.
f076c36367f : gitlab-ci: reduce a630 runner load
b7b72681bdb : meson/intel: add missing dep on git_sha1.h
d4f4546ada7 : zink: use type of src[0] for ntv store and load ops
359c9384837 : zink: add lengthy comment and remove assert from discard_if ntv pass
97ec109d8fa : zink: handle ntv case of nested loop instructions more permissively
e40a77ea5d0 : zink: use right vulkan type for GL_PRIMITIVES_GENERATED queries
b9b943793b0 : zink: only reset query pool on query end if current batch isn't in renderpass
2c02ca21842 : zink: properly handle query pool overflows
510631ad76b : zink: only stall during query destroy for xfb queries
27defcd20ed : zink: use #define for number of queries per-pool
3eea7fc88bb : zink: rework query handling
2096903a05b : panfrost: Fix outmods on int to float conversions
be8a8edb1e4 : docs/submittingpatches: add more than one `Cc: mesa-stable` example to the examples list
da23a31726f : docs/features: Update ASTC entries for Panfrost
f34b8d3609d : panfrost: Map PIPE_{DXT, RGTC, BPTC} to MALI_BCn
6da405ca777 : panfrost: Filter compressed texture formats
407a052ced4 : panfrost: Pipe in compressed texture feature mask
d5a9cd1b7dd : panfrost: Add format codes for new compressed textures
64608b4bcf8 : panfrost: Compact unused BO flag bits
c6ebff3ecdd : panfrost: Remove panfrost_bo_access type
62ec4e02f6b : panfrost: Remove PAN_BO_DONT_REUSE
d6e3808e7e7 : panfrost: Remove PAN_BO_COHERENT_LOCAL
baa1a8fbbad : panfrost: Merge PAN_BO_IMPORTED/PAN_BO_EXPORTED
0aa6de967b9 : panfrost: Index BOs from the BO map sparse array
169dbb5b08a : panfrost: Add a sparse array to map GEM handles to BOs
37d89e0f936 : panfrost: Fix write to free'd memory
20dd37024b0 : panfrost: Fix fence leak
15a17fddad6 : aco: add 32-bit integer addition to can_swap_operands
ec9920e72b0 : radv: use lower_shuffle_to_swizzle_amd
7ba645d5cb3 : nir/lower_subgroups: add lower_shuffle_to_swizzle_amd
9c317cb2787 : nir/lower_subgroups: pass options struct to lower_shuffle
a6a731bea5e : aco: implement <32-bit masked_swizzle_amd
d377fbf95d0 : aco: optimize some masked swizzles to DPP
09f48de582e : aco: read 0 from inactive lanes when using dpp
c417172751c : panfrost: Enable framebuffer fetch
317be5a16df : panfrost: Extend fetched framebuffer results
d94584c5a66 : panfrost: Always use SOFTWARE for pure formats
b9869e0e5e6 : panfrost: Generate shader variants on framebuffer bind
a3952e927ed : panfrost: Use f2fmp for framebuffer lowering conversions
d16d1367341 : panfrost: Stop keying on rt format when using native loads
391ad72812f : panfrost: Implement texture_barrier
2fbe7ca9d9c : pan/mdg: Use a 32-bit ld_color_buffer op when needed
18059f48f84 : pan/mdg: Set the z/s store intrinsic base correctly
7781d2c2ead : pan/mdg: Support MRT in output load lowering
2fa60b70e08 : pan/mdg: Handle non-blend framebuffer lowering
ed4d2739fe0 : pan/mdg: Emit a tilebuffer wait loop when needed
1e1eee992e8 : pan/mdg: Do the pan_lower_framebuffer pass later
e603248e075 : panfrost: Add a bitset of render targets read by shaders
75018f64956 : panfrost: Add rt formats to shader state
f2eced96602 : pan/mdg: Use the writeout tag for tilebuffer wait loops
61dfc3c693d : pan/mdg: Handle tilebuffer wait loops
b29027f9dc7 : panfrost: Clamp pure int pixels
4141d26ee16 : panfrost: Fix MALI_READS_TILEBUFFER
2e3a589e6c8 : nir: Add a base value to load_raw_output_pan
69ef1808374 : glx: drop always-true #ifdef
39006590517 : egl/wayland: add missing newline between functions
ae5ac4cbb6a : egl: Build surfaceless platform on Android
00ca9b81426 : radv: advertise VK_EXT_extended_dynamic_state
b2622843003 : radv: add support for dynamic vertex input binding stride
9cc99baa4ad : radv: add support for dynamic depth/stencil states
e8a69b782dc : radv: add support for dynamic and scissor count
d6c1e5051eb : radv: add support for dynamic primitive topology
52bf1035a6e : radv: add support for dynamic cull mode and front face
77499414d74 : radv: declare new extended dynamic states
2693770806e : radv: add VK_EXT_extended_dynamic_state but leave it disabled
ac575f4215d : radv: rework dynamic viewports/scissors support
7324977e420 : radv: remove the secure compile support feature
59b4c623c93 : nouveau: avoid LTO ODR warning (v2)
ac002b15d3a : nvc0: set sampler index mode to independently on gv100 compute
55776a0ae06 : radv: return VK_ERROR_DEVICE_LOST if wait-for-idle failed or expired
351b5137d71 : spirv: Allow block-decorated struct types for constants
81773b4b441 : spirv: Skip phis in unreachable blocks in the second phi pass
e086f64d393 : nvc0: set local mem size for compute on gv100
248fbe15675 : freedreno: fix layout pitchalign field not being set for imported buffers
b8df1c43d24 : nir: allow nir_lower_clip_halfz to run in geometry shaders
3fe87a58369 : nir: allow nir_lower_point_size_mov to run in geometry shader
36abb0c6918 : intel/compiler: don't propagate cmp to add if add is saturated
19ca34ed270 : aco: don't create phis with undef operands in the boolean phi pass
9a089baff1a : aco: optimize boolean phis with uniform selections
f622e80494f : aco: create better code for boolean phis with constant operands
47b0653d5dc : aco: rework boolean phi pass
05e23cb23dd : llvmpipe/cs: fix image/sampler binding for compute
54232bee06a : llvmpipe: flush resources on sampler view binding
7582f4a49cd : llvmpipe: denote NEW fs when images change.
033e933348c : nv50/ir/tgsi: move call to tgsi_scan_shader inside Source constructor
c905e485936 : bin/gen_release_notes.py: drop new_features.txt when we release XX.Y.0
7f61f4180b6 : introduce `commit_in_branch.py` script to help devs figure this out
40a6de176d0 : anv: fix uninitialized variable access
e3ddba73241 : iris: fix fallback to swrast driver
e00adef34a5 : egl: automatically compile the `drm` platform when available
60ad006b27e : meson: move xlib-lease block further down
448eb19158f : vulkan: automatically compile the `display` platform when available
a38e21d6683 : egl: always compile surfaceless
e66e0c0c2d0 : u_prim_restart: handle user buffers in util_translate_prim_restart_ib()
66ed9792edb : nv50: Clear nv50_ir_prog_info of dead and codegen specific variables
50d20dc055d : ac/llvm: export ac_init_llvm_once in targets
8da237428c1 : bin/symbols-check.py: add --ignore-symbol argument
51bdaf0b601 : st/mesa: set compressed_data to NULL when freed
ca51f75f9d3 : aco: fix more validation errors from vgpr spill/restore code
1af1eb9f7bd : gitlab-ci: Enable -Werror in `meson-gallium` job
81317e2c144 : lima: add missing break
38218ab7e20 : lima: add missing fallthrough comments
745aeba6236 : etnaviv: add missing fallthrough comments
44b1f9c6ffe : iris: Add missing break in switch in modifier_is_supported
ffb6eb6d5df : freedreno/ir3: run nir_opt_loop_unroll in optimization loop
9c23afebbe4 : freedreno/ir3: fix setup_input for sparse vertex inputs
8dfa072ed82 : intel/compiler/fs: Still attempt simd32 when INTEL_DEBUG=no16 is used
1a4a2f563b0 : intel/compiler/cs: Allow simd32 in some more cases with no8 and/or no16
9418c8ec8dd : gitlab-ci: Don't rebuild kernels and rootfs if they have been already built in mainline
1a3eb43d5b8 : gitlab-ci: do not run full CI on scheduled pipelines
1639d3c2cdf : gitlab-ci: update ci-fairy minio to latest upstream
b3fdd773854 : panfrost: Report blend shader work count
5247d673022 : panfrost: Move panfrost_translate_texture_type
816af26f027 : panfrost: Handle PIPE_FORMAT_S8_UINT
4c891488342 : panfrost: Handle PIPE_FORMAT_X24S8_UINT
1fdeef5e4a1 : panfrost: Move scoreboarding routines to common
7ec6ee40578 : panfrost: Drop batch from scoreboard routines
fa722887da1 : panfrost: Pass polygon_list to tiler init function
31197c2c1bc : panfrost: Factor out scoreboarding state
c8d848b2782 : panfrost: Move pool routines to common code
1d88f078201 : panfrost: Drop Gallium-local pan_bo_create wrapper
ed1910dc68e : panfrost: Move debug flags into the device
8958fbd29e2 : panfrost: Expose pool-based allocation API
34e0954f1d2 : panfrost: Track the device through the pool
6ef7c05746f : panfrost: Allocate pool BOs against the pool
8882d6aad63 : panfrost: Introduce pan_pool struct
5d1bff290af : docs/features: Track Panfrost
9497a1fbe72 : docs: fix a bunch of typos
49d35f3d882 : glsl: declare gl_Layer/gl_ViewportIndex/gl_ViewportMask as vs builtins
26b75daef57 : turnip: fix active_desc_sets not being set for compute pipeline
ee99a7a1cfb : docs: add some missing stuff to sourcetree.rst
27b09d293ba : docs: update calendar and link releases notes for 20.1.3
6b4aee78aed : docs: add release notes for 20.1.3
1e3aeda5281 : glsl: only allow 32 bits atomic operations on images
233af4a412d : glsl: don't expose imageAtomicIncWrap for signed image
438392243fb : ac/llvm: remove the -1 hack from ac_atomic_inc_wrap
0c8873d85db : glsl: reject size1x8 for image variable with floating-point data types
315ac941071 : gitlab-ci: Remove left-behind rules:
40526451ca5 : radv: compute prim_vertex_count at draw time
972081c6887 : radv: adjust IA_MULTI_VGT_PARAM.PARTIAL_VS_WAVE at draw time
5f1b0f4b48a : radv: adjust IA_MULTI_VGT_PARAM.WD_SWITCH_ON_EOP at draw time
9f561feecc7 : radv: store the primitive topology hardware value in the pipeline
6f734324a5e : radv: implement missing VK_ACCESS_MEMORY_{READ,WRITE}_BIT
02a57896f66 : nv50/ir: fix memset on non trivial types warning
cd67e2c280a : nine: remove unused var
8f6d66d5094 : zink: fix missing fallthrough comment
20dff7dc6b0 : v3d: remove redefine of VG(x)
03a5b3f6d5a : freedreno: fix missing fallthrough comments
40e00c800cf : amd/llvm: Mark pointer function arguments as 32-byte aligned.
d2bd77eae48 : glsl: don't validate array types in ir_dereference_variable
9ad19fff3eb : radv: use bitshifts for debug enum values
979e7e36807 : freedreno/layout: layout simplifications and pitch from level 0 pitch
4b290b759a8 : freedreno: add a fd_resource_pitch helper
344e764b012 : freedreno/a2xx: fix compressed textures
3021cb32158 : docs: Document how to interact with docker containers.
21e6d67a2e2 : docs: Relax the expectations of HW CI farms.
27c9272c3d7 : docs: Move the gitlab-ci docs to RST.
a2ca7e09fe6 : docs: Move the conformance and the CI docs to a top level Testing section.
9af82b50264 : docs: Move the current CI .rst doc to docs/ci/ and link to it from .gitlab-ci.
29cba3b6954 : nir/validate: Don't abort() until after the shader has printed
55cf97f56ed : Revert "ac/surface: require that gfx8 doesn't have DCC in order to be displayable"
0ca7bd73c6f : zink: translate gl_FragColor to gl_FragData before ntv to fix multi-rt output
1fd35630259 : nir: add lowering pass for fragcolor -> fragdata
44da0f067ca : zink: expose depth-clip if supported
ffb8020f6e7 : radv: Use correct semaphore handle type for Android import.
84ed2793ebd : radv: set depth/stencil enable values correctly for the meta clear path
fcac0b4fc9d : freedreno/regs: document CS shared storage size bit
deefebc55be : v3d/compiler: Fix sorting the gs and fs inputs
3cb2438284f : panfrost: add some missing fallthrough comments to bi_pack.c
2286c9ac21c : panfrost: hide more unused code in bi_lower_combine.c
f35283d32e3 : panfrost: add some missing fallthrough comments
7ccf2580638 : nouveau/nvc0: silence maybe-uninitialized warning
6bec54dd3e3 : iris: silence maybe-uninitialized for stc_dst_aux_usage variable
01c04a42a60 : iris: fix maybe-uninitialized warning for initial_state variable
bba766d85db : radeonsi: fix SI_NUM_ATOMS
4686a956212 : r600/radeonsi: silence zero-length-bounds gcc warnings
f472c984430 : freedreno/ir3: add support for a650 tess shared storage
75b59bb1d65 : gallium: add PIPE_SHADER_CAP_GLSL_16BIT_TEMPS for LowerPrecisionTemporaries
6aea39641a6 : glsl: lower mediump temporaries to 16 bits except structures (v2)
7f00d4dac81 : glsl: Handle 16-bit types in loop analysis
63ab8d41d1a : glsl: add capability to lower mediump array types
38cadd8b462 : glsl: lower builtins to mediump that always return mediump or lowp
8fcf8e7fd40 : glsl: lower builtins to mediump that ignore precision of certain parameters
3781697c23f : glsl: don't lower builtins to mediump that don't allow it
69f7a3dac69 : glsl: don't lower precision of textureSize
977b84652a1 : glsl: flatten a tautological conditional in lower_precision
9fccae80bef : glsl: cleanups in lower_precision
8a93d2f128b : glsl: remove the return type from lower_precision
161105d7321 : glsl: convert reusable lower_precision util code into helper functions
8d62969cfe8 : glsl: validate more stuff
8773d58b056 : glsl: run validate_ir_tree if GLSL_VALIDATE=1 regardless of the build config
82caff5bc36 : glsl: fix evaluating float16 constant expression matrices
50c27a0a170 : glsl: fix the type of ir_constant_data::u16
3e47cb185e3 : glsl: print constant initializers
42be975aa29 : glsl: print precision qualifiers in IR dumps
a038863ba07 : glsl: make print_type non-static for debugging
1d5e1882f66 : anv: Handle clamping of inverted depth ranges
3bb3e8940c9 : llvmpipe: add ARB_post_depth_coverage support.
b8fcb621340 : ci/virgl: update results after streams fixes.
d146d7bb97d : draw/gs: use mask to limit vertex emission.
72ed9e7046d : draw: free vertex info from geometry streams.
b4802d6ea13 : draw: use common exit path in pipeline finish.
3e455d6ad31 : draw/gs: reverse the polarity of the invocation/prims execution
1c9bf586e7b : draw: account primitive lengths for all streams.
09da72a7408 : gallivm/nir: end primitive for all streams.
690238ff564 : gallivm/nir: don't access stream var outside bounds
21b903dd7d9 : gallivm/gs_iface: pass stream into end primitive interface.
87a388fb29c : draw/gs: only allocate memory for streams needed.
903b5814b5c : gallivm/draw/gs: pass vertex stream count into shader build
99ae39f76c9 : draw/gs: fix up current verts in output fetching.
7d82bb0e41d : draw: emit so primitives before ending empty pipeline.
59c8fff7e47 : gallivm/nir: call end prim at end on all GS streams.
b921d17aa69 : broadcom/qpu: set VC5_QPU_RADDR_A out of the switch at _pack_branch
ec4d3def165 : aco: use VOP2 version of v_mbcnt_hi_u32_b32 on GFX6/7
b7418270c34 : util: Share a single function pointer for the 4-byte rgba unpack function.
a8e7004dc55 : util: Remove the stub pack/unpack functions for YUV formats.
abd9aa2c772 : llvmpipe: Generalize "could llvmpipe fetch this format" check in unit testing.
2da4badfe34 : util: Use designated initializers to clean up the format tables' pack/unpack.
e7010eeff03 : util: Merge util_format_read_4* functions.
2f4d557a561 : util: Merge util_format_write_4* functions.
c3d05003896 : svga: Reuse util_format_unpack_rgba().
725b27135bd : gallium/util: Move the Z/S handling to the outside of get_tile().
a2b74a5d8a1 : gallium/util: Clean up the Z/S tile write path.
019a0309073 : gallium/util: Fix location of the comment about S8_UINT handling.
377026e3ada : etnaviv: Use the util_pack_color_union() helper.
32bf7229e51 : util: Remove unused util_format_planar_is_supported().
f6f1f8e3f6d : softpipe: Clean up softpipe's SSBO load/store interpreting instructions.
18cb8f23222 : util: Mark util_format_description() as a const function.
9300a14ffba : nir: refactor nir_can_move_instr
09d0e06c5c8 : nir: also move vecN in case of nir_move_copies
14c554a391e : turnip: use global bo for clear blit shaders
10020b8d175 : aco: remove superflous (bool & exec) if the result comes from VOPC
e4654a35b00 : radv: enable zerovram for Quantic Dream games
dcd171f5e9b : gitlab-ci: More stable URL for kernel and ramdisk artifacts, for LAVA
bf3d4b1adde : gitlab-ci: Build kernel drivers for a few ethernet USB dongles
bbf2db20fef : nv50/ir/nir: fix cache mode conversion
31e344799a7 : gv100/ir: fix coherent and volatile memory access
a43eb650de4 : gv100/ir: implement sample shading
5786c63be30 : nv50/ir/nir: fix interpolation on explicit operations
77844690be7 : iris: Fix fast-clearing of depth via glClearTex(Sub)Image
026615c0f9e : docs: fixup envvar output
c8537744bba : docs: use svg for graphviz output
892fdde23f4 : docs: move gallium specific docs into gallium folder
64a4ba9e1ce : docs: add an extension to generate redirects
ce5a3524faa : docs: clean up gallium index-file
2f813981878 : merge gallium docs into main docs
cb11900cb6d : ci: add graphviz to the .docs-base template
6ff66942d26 : freedreno: Sync registers with envytools
c1ba7612fb0 : freedreno: Include adreno_pm4.xml.h before adreno_a6xx.xml.h
53e204dc26e : gallium/swr: Fix compilation warnings
846f4f95dd8 : freedreno/a6xx: Force gl_Layer to 0 when necessary
f69c3849b8c : tu: Force gl_Layer to 0 when necessary
4f91345f492 : ir3: Add layer_zero variant bit
ef67218325f : pan/decode: Make mapped memory read-only while decoding
cb5edcd2154 : panfrost: Expose MSAA 4x
a5c4fe2c78d : panfrost: Save sample_mask before blitting
bb577051dd5 : panfrost: Enable MSAA if we render to such a surface
3b7aeb2448a : panfrost: Set depth/stencil_layer_stride accordingly
5e38d956ab0 : panfrost: Identify depth/stencil layer strides
490fbce239e : panfrost: Implement alpha-to-coverage
f23cdd4f72d : panfrost: Pass sample_mask to the hardware
3e251328fad : panfrost: Identify coverage_mask
546a600ba55 : panfrost: Don't advertise MSAA 2x
211cc2550c8 : panfrost: Set layer_stride for multisampled rendering
937d3687ac7 : panfrost: Include pointer for each sample
41c06deb630 : panfrost: Index texture by sample
95afda39a66 : panfrost: Allocate space for multisampling
37204588dab : panfrost: Identify layer_stride
0b5bc6ed674 : panfrost: Set depth to sample_count for MSAA 2D
af6fc41d2c1 : pan/mdg: Use _VTX tag for texelFetch in frag shaders
63a8722c6aa : pan/mdg: Handle nir_texop_txf_ms
6d9f9512208 : pan/mdg: Handle nir_tex_src_ms_index
a2748d4796e : pan/mdg: Handle GLSL_SAMPLER_DIM_MS
d624118cc9e : pan/mdg: Allow ignoring move mode
af8fcfe6202 : pan/decode: Identify layered MSAA flag
eba9bcd3c98 : pan/decode: Fix MSAA texture decoding
797fa87ec98 : pan/mdg: Fix indirect UBO swizzles
658b59df82b : pan/mdg: Respect type/mask in mir_lower_special_reads
836d41d7726 : ir3: use empirical size for params as used by the shader
f6aa0719cfa : bifrost: Set RTZ rounding mode for f2i conversion
7682c887b32 : tu: Enable KHR_variable_pointers
9aec89ead34 : tu: Rewrite variable lowering
edc8119da4e : anv: garbage collect timeline semaphore when querying value
137d8f98897 : v3d: Enable perpendicular line caps when line smoothing
ee4d51f8b2d : v3d: Add a lowering pass for line smoothing
207da33a86d : v3d: Handle the line width intrinsics
121b82f6387 : nir: Add intrinsics for the line width
2c4616368b9 : v3d: Implement the line coord intrinsic
14dd65bb5bf : compiler: Add a system value for the line coord
3144bc1d336 : intel/perf: move query_mask and location out of gen_perf_query_counter
9f19662550a : iris: remove iris_monitor_config
bffee01bd9e : a4xx: hook up centroid ij coords
a6ed1d7fa5e : nir: Add docs to nir_lower[_explicit]_io
0bc5a829dd6 : nir: Remove shared support from lower_io
be96b069ad4 : nir: Assert that nir_lower_io is only called with allowed modes
b019b22c7ae : panfrost: Only call nir_lower_io on shader_in/out
23b7094829d : v3d: Only call nir_lower_io on shader_in/out
96d99f2eccb : vc4: Only call nir_lower_io on shader_in/out
786325fdb02 : nouveau: Only call nir_lower_io on shader_in/out
4f521e596a3 : lima: Only call nir_lower_io on shader_in/out
36a90468486 : freedreno: Only call nir_lower_io on shader_in/out
fc944428bfb : ir3: mark ucp_enables as allowed values on all keys
01a1926fb9d : etnaviv: replace prims-emitted query
42c814158b5 : a4xx: add polygon offset clamp, fix units
00f9d4b1fdb : a4xx: add noperspective interpolation support
12e18d9e7ad : nir: add vec2_index_32bit_offset address format
7ab73160032 : nir: Refactor load/store intrinsic helper
6d8e2cec819 : freedreno/regs: document SS6_UBO state src
0a7b1f91670 : freedreno/fdperf: prefer render node
385d036f583 : freedreno/fdperf: better compatible string matching
9c34a3322d8 : freedreno/fdperf: fix print of base address
85761e23ea6 : wsi/x11: Log swapchain status changes
b0bbb62325b : vulkan/wsi: Don't consider VK_SUBOPTIMAL_KHR to be an error condition
c5d8961b0b0 : Revert "radv: add support for MRTs compaction to avoid holes"
ad913a18b14 : radv: Always enable PERFECT_ZPASS_COUNTS.
ad151499583 : radv: Set handle types in Android semaphore/fence import.
7b21ce401f7 : radv: disable FMASK compression when drawing with GENERAL layout
8453d2941a7 : Revert "nir: Support sysval tess levels in SPIR-V to NIR"
2044bdac4fb : Revert "nir: Add an option for lowering TessLevelInner/Outer to vecs"
b76c6dcbc55 : freedreno/ir3: fix/rework tess levels
3c5512ce509 : freedreno/layout: fix explicit layout offset not added to slice offset
01986eaf05c : amd/addrlib: fix another C++ one definition rule violation
00d3b13837c : iris: return max counter value for AMD_performance_monitor
2f4a112ec4a : st/mesa: fix reporting of float perf counters max value
2550531dd6b : llvmpipe: enable GL 4.2
28ebc8a2125 : llvmpipe: bump to GL support to GL 4.1
df6682d7823 : llvmpipe: bump texture/scene limits to enable GL 4.1
0ca266025ab : mesa/version: only enable GL4.1 with correct limits.
1a83279da57 : turnip: enable 420_UNORM formats
7af2a0b9bcd : turnip: support multi-image layouts
37cd3c256a2 : turnip: clear_blit: pass aspect mask to setup function
ef11d5fc8bb : st/mesa: allow R8 to not be exposed as renderable by driver
9e2afe4f05a : mesa/glformats: make _mesa_gles_error_check_format_and_type() more consistent
a573c8cd47c : drirc: Add picom to adaptive_sync exclusion list
19f3c79c7ed : turnip: fix tess param bo size calculation
395511d1691 : nir: Add nir_lower_clip_disable.c to SCons build.
a1b89dbc8f4 : gitlab-ci: Enable -Werror in `meson-classic` job
ec8fdf8579d : nouveau: fix pointer-sign warning
b9e163fa67e : util: Avoid strict aliasing bugs in xxhash.
29ce8060eb0 : draw/clip: fix viewport index for geometry shaders
3366171d0ac : draw/clip: cleanup viewport index handling code.
0e7b7c30870 : turnip: vsc improvements
4ac851ea253 : turnip: rework render_tiles loop
8898ebce1a1 : turnip: make tiling config part of framebuffer state
31392f83711 : Revert "loader/dri3: Check for window destruction in dri3_wait_for_event_locked"
02d0b2d5604 : meson: Add versioning for xvmc tracker
a79ca675f3d : st/program: use nir_lower_clip_disable instead of nir_lower_clip_vs conditionally
fb2fe802f63 : nir: add lowering pass for clip plane enabling
f8946bd705c : v3d/tex: handle correctly coordinates for cube/cubearrays images
0b6e03b8481 : CI: reduce bandwidth for git pull
9190cc9b151 : tu,radv: fix potentially wrong offset of flexible array.
e2209e869a5 : meson: turn on Wimplicit-fallthrough project wide
26aa02b5ab9 : nv30: add missing fallthrough comment
651441c16fd : mesa: update fallthrough comment so gcc can see it
9549443a8f0 : svga: add missing fallthrough comments
7579414db24 : r300: add and fix up fallthrough comments
dfb9be6994f : mesa: fix unintended fallthrough in glIsEnabled()
8b90310b401 : mesa: add missing fallthrough comment to teximage.c
d88447d5ce4 : mesa/vbo: add some missing fallthrough comments
cb8cd644113 : spirv: add missing fallthrough comments
580fe899581 : radeon: add missing fallthrough comments
f692131641f : glsl: move fallthrough comment to where gcc can see it
bf3fc3cf3d5 : glx: add missing fallthrough comment
cb5fafd6178 : radeonsi: add missing fallthrough comment
5c4d9816acf : mesa: add fallthrough comments to COPY_SZ_4V()
dbf016e2597 : nir: fix implicit fallthrough warnings
31dcc173b15 : mesa: add fallthrough comments to get.c
f9310992704 : mesa: add fallthrough comments to glformats.c
040b07c7fee : mesa: fix fallthrough in glformats
8591adea38b : nir/algebraic: Don't distrubte absolute-value into dot-products
99afaa1d548 : ci: Disable pixmark-piano trace on a630 due to GPU hangs.
7b0a4f977b9 : pan/mdg: Schedule based on liveness
a6f0d7f003b : pan/mdg: Vectorize vlut operations
c957249df9d : pan/mdg: Skip r1.w write where possible
de41c4c103d : pan/mdg: Prioritize non-moves on VADD/VLUT
01e965d3122 : pan/mdg: Allow Z/S writes to use any 2nd stage unit
8ac2c080452 : pan/mdg: Defer smul, vlut until after writeout moves
2904acd9383 : pan/mdg: Schedule writeout to VLUT
14415d581a9 : pan/mdg: Remove bundle interference code
5a43f7fcce8 : pan/mdg: Don't assign destination in writeout block to r1
d838cb96a57 : pan/mdg: Defer nir_fuse_io_16 until after opts
78df3b03757 : panfrost: Specify stack_shift on SFBD
64cdc1311b9 : etnaviv: move ra into own file
027e9e8da37 : etnaviv: move nir compiler related stuff into .c file
f1df033fccd : etnaviv: move functions that generate asm to own file
79427a01909 : etnaviv: drop emit macro
624b8b4a928 : etnaviv: merge struct etna_compile and etna_state
0f025e8b810 : etnaviv: move liveness related stuff into own file
9ae96d32dd8 : etnaviv: make more use of compile_error(..)
96670c81502 : etnaviv: drop OPT_V define
1636e14cfd4 : etnaviv: move etna_lower_alu(..) to etnaviv_nir.c
7460d4863df : etnaviv: get rid of etna_compile dependency
12b15cbcbfa : etnaviv: move etna_lower_io(..) to etnaviv_nir.c
ea17cbf16fa : etnaviv: convert enums
34f776386ca : etnaviv: delete not used struct
3cdc0d50981 : ci: Move deploy stage between container & build stages
fc41ec16c8b : ci: Use "when: always" for pages job
ab9ecb607b8 : radv,vulkan: add a new x11 wsi drirc workaround for DOOM Eternal
311b9f25834 : Revert "vulkan/wsi/x11: Ensure we create at least minImageCount images."
11a6a96f8a5 : radv: fix wide lines with multisample enabled
efec833a188 : CI: Disable Windows build due to unstable infrastructure
f2f57ef9f78 : zink: implement Vk_EXT_index_type_uint8
53372175c9b : radv: fix wide points and lines
8b8ffb12b40 : docs: update llvmpipe GL 4.0 status
af7a7f6ce7b : ci: fixup tests after all indirect images fixes.
0ecae0ac0b5 : llvmpipe: handle indirect images properly
b7b22b735d1 : draw/sample: add support for indirect images
e6f7fe33244 : gallivm/nir: add support for indirect image loading
bc1ac7dc3f3 : gallivm/img: refactor out the texel return type (v2)
6e25a5a3756 : gallivm/nir: refactor image operations for indirect support.
3ca3b07fc1b : gallivm/nir: support passing image index into image code.
f75c1e83e2e : llvmpipe: pass number of images into image soa create
8a4ef09e7e0 : draw: pass number of images to image soa create
ee10f24a311 : llvmpipe: enable ARB_gpu_shader5
8807bdb1b76 : gallivm/sample: handle size unit offset
d243655d340 : llvmpipe/draw: wire up indirect offset
3b973eab73f : gallivm/sample: pass indirect offset into texture/image units
e168d148d76 : gallivm/nir: handle non-uniform texture offsets
9172e405ef6 : gallivm/nir: add texture unit indexing
52a050ea0ae : llvmpipe: add support for indirect texture access.
6dc904f6000 : draw: add support for indirect texture access
28f906ad913 : gallivm: add indirect texture switch statement builder.
8b15a08ebde : gallivm/sample: change texture function generator api
30c5cbbcd20 : llvmpipe: pass number of samplers into llvm sampler code.
6528a24cc52 : draw: pass nr_samplers into llvm sample state creation.
d55aa78615f : nir: add missing break to nir_opt_access()
b8409a6af77 : egl: move fallthrough comment so gcc can see it
0d5427fa44a : iris: add missing fallthrough comment
1a8f9180503 : intel/compiler: add and fix up fallthrough comments for gcc warnings
512db7ec78a : anv: update fallthrough comment so gcc sees it
06dc2f3f475 : gallivm: add missing break
2ed35c71020 : llvmpipe: add missing fallthrough comments
de4004f8ba7 : i965: add and fix fallthrough comments
8da810a7fbc : intel/compiler: Don't emit no-op cr0 changes
fe14dc98bfe : intel/compiler: Add assert that set bits are within mask
29e2a3b8f5e : gallium,util: undef ALIGN on FreeBSD to prevent name clash
f678811b567 : i965: Explicitly cast value to uint64_t
565a80450d2 : iris: Explicitly cast value to uint64_t
708db983dd0 : meson: Do not enable USE_ELF_TLS for FreeBSD
6cba468b5e7 : gitlab-ci: Do not create the "success" job when the test-docs job exists
8e2cb8ef276 : gitlab-ci: Extend .ci-run-policy template for docs jobs
1c612e8c094 : gitlab-ci: Use rules: instead of except:/only: for test-docs job
196ac4c6f3f : ci: move test-docs to container stage
28ca70b6b64 : ci: move deploy-stage later in the pipeline
8774707b1e3 : ci: test docs for non-master builds
24fe9f43e56 : ci: only build docs if any docs changed
d1ca80235de : ci: only build docs in the upstream-repo
9bebbf58678 : freedreno/ir3: add support for INTERP_MODE_NOPERSPECTIVE
0f5c9f97131 : turnip: set missing bary sysvals
2453f2bdb73 : freedreno/a6xx: set missing bary sysvals
dadfb4ec587 : freedreno/a5xx: set missing bary sysvals
33457fc705d : freedreno/ir3: add generic get_barycentric()
75fef41f16c : freedreno/a4xx: fake LINEAR_PIXEL varying support for u_blitter
0d419c76bb0 : freedreno/a3xx: support LINEAR_PIXEL/PERSP_CENTROID/LINEAR_CENTROID sysvals
2e9ded21d14 : freedreno/registers: update varying-related registers
549b4a3dd4a : gitlab-ci: Automatically run pipelines for Marge Bot pre-merge only
8456ff75b39 : v3d/compiler: fix image size for 1D arrays
5f1a16d06d8 : st/mesa: do not clear NewDriverState for inactive states
7940b47de64 : gallium/docs: remove unused imgmath extension
27dcdbcc96c : gallium/docs: remove non-existent static dir
1d7bb2dde0d : gallium/docs: prefix exts dir with underscore
47d3b80428c : gallium/docs: use none for highlight_language
686f6c72068 : gallium/docs: remove reference to non-existent label
686cf8eaada : gallium/docs: fixup formatting of numbered lists
7f5061c0b78 : gallium/docs: update to recent sphinx
2bf2e6c83d2 : draw/llvm: fix big-endian mask adjusting
0e6dfd11f22 : mesa/get: fix enum16 big-endian getting.
b743c9bf2d5 : llvmpipe: fix occlusion queries on big-endian.
3aeb61da49c : gallivm/nir: fix big-endian 64-bit splitting/merging.
92866052769 : glsl: fix constant packing for 64-bit big endian.
2cd466bf340 : docs: add a page explaining the GitLab CI and the Intel CI
fde25a6ed94 : mesa/swrast: use logf2 instead of util_fast_log2
2e5b2145068 : anv: disable i915_perf warning on non-Linux
5a27efdf0e3 : meson: Revert commit overriding C++ standard with gnu++11 on ppc64el
cd7acd09b9f : clover: Fix types collision between c++ and altivec
54d7907c276 : nir: Propagate *2*16 conversions into vectors
3e3958c44f7 : panfrost: Do fine-grained flushing for occlusion query results
b1d309eaa39 : freedreno/a4xx: fix *_NONE enum conversion
fa673920483 : CI: Re-enable Panfrost T860 jobs
50d75536009 : radeonsi: add a debug option to enable NGG culling for tessellation
b0c77a5f1d4 : radeonsi: don't try to enable NGG culling for GS
90cf741d316 : radeonsi: always use Wave64 for HS/GS/VS shader stages (except GS fast launch)
9049e39804c : radeonsi: always use Wave32 for GS fast launch, because Wave64 hangs
8fff9beb44b : radeonsi: fix NGG culling for Wave64
2866a6f78d2 : ac/gpu_info: fix num_physical_sgprs_per_simd for gfx10
1401fc055c5 : radeonsi: don't flush in fence_server_sync
34db50558d9 : CI: Temporarily disable Panfrost T860 jobs
bb703d42479 : CI: Re-enable the Windows VS2019 build job
e3e1e9f82ca : CI: Correct build-directory path on Windows, and keep it
ee056dfef6e : CI: Try shared libraries on Windows
97b4b1254ec : CI: Enable assertions on Windows
5a05f9714bb : radeonsi: bump SI_NUM_SHADER_BUFFERS to 32
7e8cfc0add8 : glsl: remove stale FIXME
64a2500a697 : st/glsl_to_nir: disable st_nir_lower_builtin() when packing supported
4cca5137aed : glsl: define gl_LightSource members in ARB_vertex_program order
5ddab654d93 : mesa: add _mesa_program_state_value_size() helper
0e7b1a6b1a5 : mesa: remove _mesa prefix from static function
849227d70f3 : zink: set lower_uadd_carry in nir options
d7d76878298 : loader/dri3: Check for window destruction in dri3_wait_for_event_locked
7c226116c6c : loader/dri3: Use dri3_wait_for_event_locked in loader_dri3_wait_for_msc
ee77951714f : loader/dri3: Add dri3_wait_for_event_locked full_sequence out parameter
08c39a8a293 : v3d: Fix -Wmaybe-uninitialized compiler warning in the v33 code.
f55a308c75d : v3d: Enable PIPE_CAP_TGSI_TEXCOORD.
a60e8dfdc5d : vc4: Enable PIPE_CAP_TGSI_TEXCOORD.
64cb81a3a4a : gallium/util: Add a helper function for point sprite handling.
622c548967a : turnip: enable depthBiasClamp
0ed100ea498 : turnip: enable largePoints
cb10edd5446 : freedreno/regs: add extra bits for UBWC array pitch
c425ca5566a : frontends/va: Handle dynamic resolution/SVC for VP9
653dff949e9 : v3d/compiler: fix spill offset
7a5e6fd25f2 : radv: add support for MRTs compaction to avoid holes
4e0dcbb8808 : radv: use SPI_SHADER_ZERO for non-written color attachments
18b42eebd59 : radv: rework 8/16-bit color attachment formats detection
76ee45d3a88 : radv: adjust CB_SHADER_MASK for dual-source blending in the shader info pass
26a48d8d352 : radv: enable VK_AMD_shader_ballot on GFX6-7 with both compiler backends
cff418cc4ca : nir: Add new rules to optimize NOOP pack/unpack pairs
237d7284180 : gallivm/nir: fix const loading on big endian systems
7d31bc9a34c : freedreno/ir3: fix resinfo wrmask
b1c16e52514 : docs: use ref-links for internal references
5ee55b206af : docs: fix internal references
1d250bf2916 : docs: restore accidentally dropped labels
05e61a91573 : docs: remove non-existent reference
3b74e6fa280 : meson: Do not require shader cache for radv.
c0c03f4772f : rbug: Fix rbug_delete_vs_state lock acquisition.
583d7d3d8d0 : v3d: moving v3d simulator to src/broadcom
4fccbd0ea60 : turnip: Put VK_KHR_external_fence_fd stubs back
39f06e28485 : iris: Implement pipe->texture_subdata directly
34630fe081b : turnip: Properly return VK_DEVICE_LOST on queuesubmit failures.
487576e3cfd : turnip: Fix error handling of DRM_MSM_GEM_INFO ioctls.
e67c2e1c96c : turnip: Do better TU_DEBUG=startup logging of drmGetDevices2() failure.
aba8c579a97 : turnip: semaphore support.
6283da34a91 : ci/baremetal: Bump the kernel to a recent drm-msm-fixes for msm semaphores.
5c0f82b0d72 : aco: fix partial copies on GFX6/7
66482303f6d : mapi: x86: Fix dynamic entries in x86 tsd stubs.
63805ccd3f0 : ci/bare-metal: Fail early when we get stuck powering on a cheza.
189a0fecf54 : freedreno/ir3: move nir finalization to after cache miss
f97acb4bb4b : freedreno/ir3: disk-cache support
6aadb00e60f : freedreno/ir3: build binning variant at same time as draw variant
83b97bf161f : freedreno/a6xx+ir3: stop generating pointless binning shaders
fdbe1ffaf74 : freedreno/ir3: shuffle some variant fields
c0f22c3d940 : freedreno/ir3: add ir3_compiler_destroy()
f1ab57359c7 : freedreno/ir3: move finalize_nir to pscreen hook
d3ae5593783 : freedreno/ir3: add ir3_finalize_nir()
e35b8971a74 : zink: use OpFUnordNotEqual for nir_op_fne
765de33d3ce : zink: set lower_mul_high and lower_rotate in ntv compiler options
49c13fccf75 : zink: handle isign alu in ntv
21fe5b0ffdf : zink: handle ixor in ntv
651d093298d : zink: lower byte/word extract ops in nir
90d34558488 : zink: add bitfield_reverse handling to ntv
957d8e26582 : zink: add ult handling for ntv
2159aa0c49e : zink: handle signed and unsigned min/max ops in ntv
f13d79f519d : radv: remove the load/store workaround for Monster Hunter World with LLVM
a30ad8cb238 : radv: remove the shader ballot workaround for Youngblood with LLVM
099916384a4 : docs: update favicon
2fbc12a0ac0 : turnip: fix huge scissor min/max case
1854eeefded : turnip: fix VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VULKAN_1_1_FEATURES
6b886fbc0b2 : panfrost: Add PAN_MESA_DEBUG=gl3 flag
1288613f1c7 : freedreno/a6xx: use firstIndex field
ba5e1c5310f : tu: Pass firstIndex directly to CP_DRAW_INDX_OFFSET
259d07a2ff8 : freedreno/registers: Label firstIndex field in CP_DRAW_INDX_OFFSET
a32fb2f9d03 : freedreno: On a5xx+ INDX_SIZE is MAX_INDICES
1dd24bf27b2 : freedreno: Share constlen between different stages properly
d9dd989d2a5 : freedreno: Refactor ir3_cache shader compilation
8ad65609da3 : tu: Share constlen between different stages properly
48b1602b506 : ir3: Add ir3_trim_constlen()
9edff0cfd4f : ir3: Support variants with different constlen's
4554b946c38 : ir3: Include ir3_compiler from ir3_shader
2841bb1fac8 : ir3, freedreno: Round up constlen earlier
4845f184d76 : v3d/compiler: don't rewrite unused temporaries to point to NOP register
3b1c511b099 : v3d: Use stvpmd for non-uniform offsets in GS
dab8a9169c1 : v3d: Add missing macro for stvpmd instruction
71794567f96 : radeonsi: remove tabs
0cdec11d953 : radeonsi: clear per-context buffers at the end of si_create_context
da78d50bc87 : radeonsi: make si_pm4_cmd_begin/end static and simplify all usages
7b2a0f880b5 : radeonsi: disallow adding BOs into si_pm4_state except 1 shader BO per state
3b1e42d2c22 : radeonsi: make wait_mem_scratch unmappable
428360662f3 : radeonsi: don't add the tess ring buffers into the cs_preamble state
1c1d34a67ac : radeonsi: rename init_config states to cs_preamble states
bbc0a2d51db : radeonsi: don't add the border color buffer into the init_config state
c7680625c36 : ac,winsys/amdgpu: align IBs the same as the kernel
556f4458fe9 : amd: add proper definitions for NOP packets
276e6d7bbce : gitlab-ci: attach the Fossilize log file as artifact on failure
4954df417c7 : gitlab-ci: append Fossilize stdout/stderr to a file to reduce spam
b24b415013e : gitlab-ci: set the number of Fossilize threads to 4
be5d06106ff : panfrost: Only copy resources when they are in a pending batch
66df2ffa36a : anv: Align "used" attribute to 64 bits.
293221dddae : iris: Align last_seqnos to 64 bits.
2fd746e98e7 : ci: Remove a stray "always" on the freedreno traces job.
50e20cb0361 : freedreno/a6xx: Add support for polygon fill mode (as long as front==back).
72c0522db28 : turnip: Add support for polygon fill modes.
daee177ca02 : freedreno/a6xx: Define the register fields for polygon fill mode.
b88c46fa11a : ci: Add a freedreno a630 tracie run.
b5f727afeb3 : ci/tracie: Fix apitrace dump using "less" which isn't in the ARM rootfs.
9f1412cf3eb : ci/tracie: Print the path if the trace isn't found.
7406d627c88 : ci: Include trace replay support in ARM rootfses.
acf9d8b75d9 : ci/bare-metal: Don't include dev packages in arm*test.
9079b53987e : ci/bare-metal: Skip setting of unset variables at startup.
21b2dac7930 : ci: Move ARM rootfses to stable
a04672a1052 : ci: Don't call renderdoc's ReplayController.Shutdown()
62de79ac449 : turnip: implement VK_KHR_shader_draw_parameters
16a9e233da9 : freedreno/ir3: add support for load_draw_id
01799b3448c : freedreno/registers: add CP_DRAW_INDIRECT_MULTI
7e98f2534c3 : gitlab-ci: add a list of expected failures for RADV/ACO on NAVI14
63e1e7209c2 : radv: enable ACO by default
db0afb38007 : radv: change use_aco -> use_llvm
b78f64507e9 : radv: introduce RADV_DEBUG=llvm option
37e7a5e746d : zink: unify code for setting resource barriers
a102896cff2 : radv: lower 64-bit dfloor on GFX6 for fixing precision issues
c84f11e7b67 : radv: lower 64-bit drcp/dsqrt/drsq for fixing precision issues
82b46667836 : iris: Honor scanout requirement from DRI
ec7b55f4cc5 : vulkan/overlay: fix crash on destroying NULL swapchain
8c962f5f61f : gitlab-ci: add parallel-rdp fossils
6da06479878 : freedreno/ir3/ra: fix pre-color edge case
c5b990f435e : turnip: disable early_z for VK_FORMAT_S8_UINT
04148f44111 : turnip: fix update_stencil_mask
9c0ae5704d6 : turnip: fix empty scissor case
7c008c293d7 : freedreno: handle batch flush in resource tracking
16b4da3ba31 : freedreno: split out batch clear tracking helper
ad136945e6d : freedreno: split out batch draw tracking helper
d74554b1674 : freedreno: make foreach_bit() declare it's cursor
1fd2bc10dc7 : turnip: implement VK_EXT_vertex_attribute_divisor
8018b4b7071 : docs: fix 20.1.2 relnotes
804c6ee0dfd : docs: update calendar and link releases notes for 20.1.2
e94f81e9df8 : docs: Add release notes for 20.1.2
3065c4bf925 : freedreno/ir3: switch PIPE_CAP_TGSI_TEXCOORD
e6d650353a0 : freedreno: convert builtin blit VS prog to ureg builder
b5574c51654 : freedreno/a3xx: use point-coord helper
ba6e1514f59 : freedreno/a4xx: use point-coord helper
3e8c6312c70 : freedreno/a5xx: use point-coord helper
a474d48e176 : freedreno/a6xx: use point-coord helper
68d6aa3dd02 : freedreno/a6xx: de-duplicate vinterp/vpsrepl state building
022c363cfbb : freedreno/ir3: add helper to determine point-coord inputs
64c2a10707f : turnip: move some logic out of create_render_pass_common
c9c76f68320 : turnip: use RenderPassCreateInfo for render_pass_add_implicit_deps
e4099201bcd : turnip: replace a memset(0) with zalloc in CreateRenderPass
70046145d19 : turnip: translate CreateRenderPass to CreateRenderPass2
01e2893cba4 : turnip: implement depthBounds
a9d866910c5 : freedreno/registers: a6xx depth bounds test registers
4fc0499049f : aco: remove outdated assert in handle_operands()
7cad27831d2 : aco: ignore blocked registers when checking edges in get_reg_impl()
91a82d00696 : radv: fix checking the return value of cs_finalize()
86df5283a32 : gitlab-ci: update the list of expected failures for Pitcairn
aa35670fd09 : radv: Make radv_alloc_shader_memory static.
64a92ef7a26 : radv/winsys: Distinguish device/host memory errors.
a5cb88eea45 : radv: Handle mmap failures.
04765e6a9a4 : radv/winsys: Deal with realloc failures in BO lists.
519ddfd3126 : aco: improve vectorization of 8/16-bit loads/stores
ddffcf36277 : aco: fix when sub-dword create_vector operand cannot be placed perfectly
91fd53884dc : aco: don't allow partial copies on GFX6/7
76b5d72921c : aco: align swap operations to 4 bytes on GFX6/7
91d7e401763 : aco: don't create byte-aligned short loads
c3259b6e6a2 : aco: add missing bld.scc() in byte_align_scalar()
a0f6ca4393d : aco: don't store byte-aligned short stores
a18da83d184 : aco: fix copy+paste error in split_buffer_store
841fdfcd453 : radv/aco,aco: allow SMEM SSBO loads on GFX6/7
35b5e1fc7c5 : aco: allow SMEM for some sub-dword accesses
c702f8ed157 : aco: only use SMEM if we can prove it's safe
0cfee26bee3 : radv: fix image variable types in meta shaders
c344c083fc7 : spirv: set variables to restrict by default
1be67d610f4 : android: freedreno/ir3: simplify generated sources rules
41683157e77 : android: freedreno/ir3: add missing generated sources and rules
b41828c3375 : android: freedreno: add fd5_layout.c to Makefile.sources
5f97dfc4c84 : vulkan/wsi/x11: Ensure we create at least minImageCount images.
7b3976d3f86 : zink: clamp VkImageCreateInfo.arrayLayers to 1 for image resource creation
994224bc293 : gitlab-ci: update the list of expected CTS failures for RADV/ACO
6a5fb31fefb : nir: Fix divergence analysis for tessellation input/outputs
8278a46b26a : intel: Disable loading drivers on DG1 devices for now
32455b657f6 : CI: Disable Panfrost Mali-T820, Lima Mali-400 and Lima Mali-450 jobs
7f48c6b6a28 : iris/compute: Split out iris_load_indirect_location
6557c8294da : iris: Split walker and state update into iris_upload_gpgpu_walker
ecf3335eef8 : anv/cmd_buffer: Split GPGPU_WALKER out to emit_gpgpu_walker
759b7f83dd7 : anv/pipeline: Split VFE/INTERFACE_DESCRIPTOR out to emit_media_cs_state
a5918ac63e8 : turnip: use pipeline cs for shader programs instead of separate bo
a58de1b8d3a : turnip: fix ts_cs_memory typo
bf92f041fe5 : freedreno: Handle DRM_FORMAT_MOD_INVALID in shared code
561aaeeb48e : intel/eu: Add the RNDU opcode
e0ab48e3ea0 : intel/eu: Set the right subnr for ALIGN16 destinations
8a0d772dca3 : intel/eu: Add a brw_urb_dest_msg_type helper
2c762955d41 : intel/eu: Add a brw_urb_desc helper
ecda98fbb2d : intel/compiler: Expose brw_texture_offset to C
479797e1304 : intel/fs: Move more prog_data setup into populate_wm_prog_data
fc519cad57b : intel/fs: Break wm_prog_data setup into a helper
2687ec5ee68 : intel/fs: Expose a couple of NIR lowering helpers
bfc1fd22cdf : iris: Delete useless #define
ba15bb383f0 : nir: only uniforms with dynamically_uniform offset are dynamically_uniform
2a61a8d95a8 : bin/symbols-check: explain C++ symbols workaround
20e12d9ef4e : turnip: implement CmdDrawIndirectByteCountEXT
6cf87d777a2 : turnip: enable VK_EXT_index_type_uint8
52da27aedee : turnip: refactor CmdDraw* functions (and a few fixes)
98b0d900474 : turnip: rework streamout state and add missing counter buffer read/writes
99eecd3775d : docs: add planning for 20.2
3f04914713b : docs: add some padding to the release calendar
ade7c3338ae : ci: remove some freedreno a6xx skips
012b7aab260 : driconf: add workarounds for SPECviewperf13
ca719c6e303 : glsl,driconf: add allow_glsl_120_subset_in_110 for SPECviewperf13
f8e8701cf1b : radeonsi: replace ctx->screen with sscreen in si_flush_gfx_cs
470b319813b : radeonsi: don't wait for idle at the end of gfx IBs
57606c2ab5c : gitlab-ci: stop testing RADV with LLVM
0aca04afa58 : aco: fix printing ASM on GFX6-7 again
e0518800a12 : gitlab-ci: Update CTS runner
287bf5f2088 : gitlab-ci: Test virgl with Khronos' OpenGL CTS
2102d5eda52 : gitlab-ci: Add manual tests for Virgl using GLES on the host
4417e924bf7 : gitlab-ci: Run more dEQP tests for virgl
a2d7f4fe5a5 : glthread: handle ARB_vertex_attrib_binding
66c2c9c6a95 : glthread: rename non_vbo_attrib_mask -> user_buffer_mask, attribs -> buffers
2bf425431d8 : glapi: fix incorrect param names in ARB_vertex_attrib_binding functions
2b8b62c55bb : ac/nir: fix 64-bit division for GL CTS
3fec2f67c3d : radeonsi: compact MRTs to save PS export memory space
6ac99b9f39d : anv: Bump the advertised patch version to 145
a9ee1b9cf95 : vulkan: Update Vulkan XML and headers to 1.2.145
677c1bd0559 : docs: cat maintainer keys to a single file
b4335aaf0ed : docs: drop deleted file from extra sphinx files
c72832e83c6 : anv: Make use of devinfo has_aux_map field
8c36936832b : iris: Make use of devinfo has_aux_map field
4be31ebb615 : gitlab-ci: drop gettext from the build images
04e8eaf4e82 : util: rename xmlpool.h to driconf.h
2ef983dca61 : driconf: drop now unused translation facility
b1f647a3b4c : driconf: drop 9% swedish translation
0a19565592a : driconf: drop 8% dutch translation
56d76859fa5 : driconf: drop 6% french translation
a029eafba36 : driconf: drop 26% spanish translation
29ee6f6c6a1 : driconf: drop 15% german translation
ae7759eb210 : driconf: drop 28% catalan translation
6e24047573f : zink: use correct define value for reserved slot count in ntv
c323e0ddf3d : intel/dev: Add device info for DG1
37a724e4ae0 : anv/dg1: Don't use SET_TILING kernel uapi.
e6588354360 : iris/bufmgr: Do not use map_gtt or use set/get_tiling on DG1
762e601f776 : intel/devinfo: Add function to check for DRM_I915_GEM_GET_TILING.
86617c08cc9 : intel/l3: Return the URB size from devinfo for DG1
793b4092416 : intel/isl: Update mocs for DG1
3daa8667512 : intel/l3: Add DG1 L3 configuration
633dec7163e : anv: Set L3 full way allocation at context init if L3 cfg is NULL
e2e0521ecbb : iris/l3: Enable L3 full way allocation when L3 config is NULL
6054b24f584 : intel/l3: Allow platforms to have no l3 configurations
49fe43e15fd : intel/l3: Don't rely on cfg entry URB size being 0 as a sentinal
f1fba99695f : intel/devinfo: Add is_dg1 to device info
64ccb740281 : turnip: Enable tessellationShader physical device feature
497671be35f : ir3: Unconditionally enable MERGEDREGS on a6xx
7a836ec6319 : turnip: Force sysmem for tessellation
2718353b381 : turnip: Support tess for draws
08aaa3d4c46 : turnip: Emit HS/DS user consts as draw states
8cb226b2588 : turnip: Update VFD_CONTROL with tess system values
f08a80dcd49 : turnip: Allocate tess BOs as a function of draw size
eefdca2e2f5 : turnip: Parse tess state and support PATCH primtype
ff16e72545b : turnip: Offset by component when lowering gl_TessLevel*
b09e690f3b7 : turnip: Lower shaders for tessellation
d2df0761200 : nir: Add an option for lowering TessLevelInner/Outer to vecs
d2d4677b56e : nir: Support sysval tess levels in SPIR-V to NIR
ffc4d82438d : v3d: Disable PIPE_CAP_PRIMITIVE_RESTART
1fc346d2bec : mesa: Add PrimitiveRestartFixedIndex to gl_constants
bb5fc90135f : gallium: Add pipe cap for primitive restart with fixed index
bcf6a9ec635 : nv50/ir/ra: fix memory corruption when spilling
b8c77d4765d : nv50/ir/ra: convert some for loops to Range-based for loops
361fb38662f : panfrost: Copy resources when mapping to avoid waiting for readers
65b3b08aaf4 : panfrost: Update sampler views when the texture bo changes
96300120609 : panfrost: RGBA4 and RGB5_A1 framebuffer support
b96d4449f44 : pan/mdg: Fix max_comp calculation for constant printing
5b351c801e0 : pan/decode: Add missing wrap modes
e219f045923 : pan/decode: Fix helper invocations when tracing
97318994bcc : r600/sfn: Don't set num_components on TESS sysvalue intrinsics
43c23ba9bff : r600/sfn: Add support for shared atomics
033968a94ea : r600/sfn: Add lowering pass for shared IO
14591a45b73 : nv50/ir/nir: rework CFG handling
8af22703e90 : nv50/ir/nir: rework input output handling
c31d711913e : nv50/ir/nir: handle clip vertex for tess eval shaders
636cf22a1f4 : nv50/ir/nir: don't emit a restart with set a stream_id
cc71fccb754 : nvc0: enable spirv caps with nir
e476629853b : nv50/ir/nir: fix nv_viewport_array2
984e930b2fc : nv50/ir/nir: fix ext_demote_to_helper_invocation
b78c3375904 : nv50/ir/print: add missing VIEWPORT_MASK handling
aecca24d03a : nv50/ir/nir: add workaround for double vertex attribs
83d2a73b73a : aco: improve validation checks for readlane/writelane
f03a5f6cac9 : radv/aco: implement logic64 instead of lowering
9a389322c44 : nir: slight correction to cube_face_coord constant folding
c95d258d1bc : aco: fix printing ASM on GFX6-7 if clrxdisasm is not found
053df9bd8f2 : v3d: Let scheduler know GS doesn’t have shared I/O memory
ed29b576cbc : nir/scheduler: Add an option to specify what stages share memory for I/O
28e3209985f : nir/schedule: Store a pointer to the scoreboard in nir_deps_state
0a18c935e15 : v3d: Remove unused member of v3d_compile
df8dc30cea7 : nir/scheduler: Handle nir_intrinsic_load_per_vertex_input
281f777433f : gv100/ir: fix OP_TXG for shadow textures
42b9aa5f5c7 : gv100/ir: fix shift lowering
a5445010e46 : gv100/ir: fix atom cas
eb6c546493b : freedreno/a4xx: simplify setup_slices
6c92a4004cc : freedreno/a4xx: restore pitch to bytes change to layout code
2cc51b0dfff : vulkan/wsi: Really terminate DRM lease in wsi_release_display().
82815bc9803 : freedreno/ir3: split ubo analysis/lowering passes
e0f93f68986 : freedreno/ir3: splitup get_existing_range()
f2226acd744 : freedreno/ir3: split out ubo info from range
0c32403c733 : turnip: remove unnecessary OVERFLOW_FLAG_REG check
df2e54f7d4c : freedreno/a6xx: remove unnecessary OVERFLOW_FLAG_REG check
ffecaedf697 : freedreno/a6xx: VSC "STRM_ARRAY_PITCH" is "STRM_LIMIT"
c977567db65 : radv: enable radv_no_dynamic_bounds for more Path of Exile executables
08f64f91d12 : gallium/util: add missing include
2d6059d8877 : gallium/util: limit STACK_LEN on Windows
e6fa8ed9685 : graw/gdi: do not depend on UNICODE macro
eda68414205 : gallium/os: call "ANSI" version of GetCommandLine
04f77595f0b : intel/compiler: Always apply sample mask on Vulkan.
19b2ac2bb9e : radv: enable radv_no_dynamic_bounds for Path of Exile
f4a643f65e3 : radv: add new drirc option radv_no_dynamic_bounds
3915b56e39c : iris: Support I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS
2305ab69382 : iris: Refactor modifier_is_supported for gen12
c19492bcdb9 : iris: Handle importing aux-enabled surfaces on TGL
4ed6e43988e : gallium/dri2: Support I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS
b25fedeff99 : isl/drm: Support I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS
9dea3e1b477 : iris: Use ISL_AUX_USAGE_GEN12_CCS_E on gen12
230952c2101 : iris: Don't support sRGB + Y_TILED_CCS on gen9
db5d98cde82 : intel: Add ISL_AUX_USAGE_GEN12_CCS_E
d9f7fce83c1 : ci: Enable NIR validation on a630 GLES2 and VK tests.
6ee80d8e0cf : ci: Bump vulkan CTS to 1.2.3.0.
f8961ea0865 : iris: Disable sRGB fast-clears for non-0/1 values
48a3f4c44b6 : iris: Avoid fast-clear with incompatible view
fbbf79377bc : iris: Remove the CCS_D fallback
e533232d8c8 : iris: Drop can_fast_clear_color's format parameter
7b7d28ed6de : docs: move "stable" tag explanation next to `Fixes:`
a096d410941 : docs: move `Fixes:` tag explanation to its own section
7488d491072 : docs: make it clear that the tags needs to be in the commit message
731465192a9 : docs: reword a sentence a bit
5d27d5eb614 : docs: add some formatting to the "backport merge request" option
0e4eb7b86d9 : docs: prefer `Fixes:` over `Cc: mesa-stable`
8fd98931235 : docs: drop `git sendemail` instructions
a29a1588b1c : docs: reword "sending a patch revision" to "updating a merge request"
fdebba27709 : docs: stop considering `Cc: mesa-stable` as an email address
b1a98a1107a : freedreno/a6xx: Set index buffer size to bo size
2580e4f9210 : freedreno/a6xx: Don't write REG_A6XX_RB_SRGB_CNTL in restore
77c50891b65 : anv: Use resolve_device_entrypoint for dispatch init
e94a122642f : docs: suggest alternative installation methods for meson
cca9aa4dfd5 : turnip: Fill out VkPhysicalDeviceSubgroupProperties
292ade3c9d2 : zink: use int assignment for vk int type
8f11cc4cad7 : freedreno/ir3: move output_loc to variant
640ff0e847f : freedreno/ir3: move const_state back to variant
00926954c30 : freedreno/ir3: un-embed const_state
ab74b792d4b : freedreno/ir3: move num_reserved_user_consts out of const_state
74140c2e859 : freedreno/ir3: convert over to ralloc
6039d083f78 : freedreno/ir3: pass variant to ir3_create()
65660622a1f : ir3: Split out variant-specific lowering and optimizations
f4654c458f8 : freedreno/ir3: constify shader key
91ed8b7fe37 : freedreno/ir3: drop shader->num_ubos
70fbd48b3a8 : freedreno/ir3: move ubo_state into const_state
a8b995c055f : freedreno/a6xx: defer userconst cmdstream size calculation
bd55533f5b0 : freedreno/ir3: add accessor for const_state
1e8808a4a0f : freedreno/ir3: refactor out helper to compile shader from asm
b6db703e0f0 : st/mesa: make texture views inherit compressed_data storage
993c64e6fe7 : ac/llvm: load 1 byte at a time if unaligned on gfx10
bddfbfcb561 : r600/sfn: Handle memory_barrier
34e15cd610c : r600/sfn: Take SSBO buffer ID offset into account
5aef9ea2a3c : r600/sfn: Add support for reading cube image array dim.
e458683a525 : r600/sfn: Add support for image_size
249dbcb769b : r600/sfn: Add imageio support
b303540c48c : r600/sfn: lower image derefs
2ac5cce1a13 : radv: require LLVM 11+ for GFX 10.3 if not using ACO
dc698fb5dc3 : radv: add support for Sienna Cichlid
8c144482ea1 : aco: replace == GFX10 with >= GFX10 where it's needed
3c28438094b : radv: replace == GFX10 with >= GFX10 where it's needed
1f871062764 : intel/tools: Add assembler tests for the cr0 register
e573f21edd3 : intel/tools: Disallow control subregisters > 3
cc6fc963f02 : intel/tools: Require explicit regions/types for special regs
9feb6302f93 : intel/tools: Drop srctype from ipreg
27557e71102 : intel/tools: Remove unnecessary reg number checking
f8110226baa : turnip: move enum translation functions to a common header
f7cc7079b0d : aco: use the same regclass as the definition for undef phi operands
897a47d8477 : aco: fix edge check with sub-dword temporaries
747e808697c : mesa/main: fix inverted condition
4bc5110eea2 : nv50/ir/nir: remove image uniform hack
c0bbca5c230 : nv50/ir/nir: handle image atomic inc and dec
3af27bb7de6 : nv50/ir/nir: move away from image_deref intrinsics
feb83f2f822 : nir/lower_images: handle dec and inc
43faa9ebb1c : nir/lower_images: fix for array of arrays
e35e0307cb6 : st/mesa: lower images when needed
365d0aa6c54 : aco: shrink mad_info
917260710f6 : aco: make ssa_info::label 64-bit
47ca84a96d7 : aco: shrink ssa_info
19983d3d4aa : radeon/vcn: bump vcn3.0 encode major version to 1
2be131f538c : radeon/vcn/enc: Re-write PPS encoding for HEVC
9d5d4f9eaac : radeon/vcn: add vcn 3.0 encode support
946c5c6b753 : radeon/vcn/dec: add db_aligned_height to message buffer
384195b041d : radeon/vcn: add Sienna to use internal register offset
909037b557c : radeon/vcn: reset the decode flags from message buffer
3817fa7a4d1 : aco: fix WQM handling in nested loops
8ce8895b69a : st/mesa: account for "loose", per-mipmap level textures in CopyImageSubData
9760a7ed913 : virgl: apply bgra dest swizzle and add Portal 2
c95b250a4c2 : turnip: set the API version
fa149b996d1 : radv: only requires LLVM 9 for GFX10 if not using ACO
4cf4fe9d821 : Revert "CI: Disable Panfrost Mali-T820 jobs"
4793c2bcb95 : Revert "CI: Disable Lima jobs due to lab unhealthiness"
70cc80805ce : radv: compute CB_SHADER_MASK from the fragment shader outputs
b848d88059b : radv: make sure to set CB_SHADER_MASK correctly for internal CB operations
270eeb41052 : docs/features: remove driver-list for forward-compatible context
eab3cabb9de : docs/features: update ARB_texture_buffer_object line
2a6a21ceb31 : docs/features: mark GL3 as complete for zink
c4aa64b4c34 : radv: lower discards to demote to workaround a RDR2 game bug
34499de5b37 : glsl_to_nir: fix vote_any/vote_all
c9976f5e4ab : glsl_to_nir: fix shader_clock
8505e6757b2 : glsl_to_nir: fix is_helper_invocation
f94ba1555d4 : spirv: drop some dead code
f43a2cd1d96 : spirv: atomic_counter_read_deref is not vectorized
0a84d22bf2b : turnip: fix renderpass gmem configs when there are too many attachments
b6b98e95106 : turnip: fix a sample shading case
ff2efd095e5 : turnip: fix a crash when rasterizerDiscardEnable is set
31a66cbe5d9 : docs: remind release maintainers to sign the tarballs and publish their key
c75e46f6d60 : docs: publish our release maintainers' keys
1d54fb5b2b5 : freedreno/ir3: update obsolete comment
5baf430261d : freedreno/computerator: MERGEDREGS update
0e0d4daa5b1 : turnip: set .MERGEDREGS based on variant
c6632c087d3 : freedreno/a6xx: set .MERGEREGS based on variant
1cc4cf141a8 : freedreno/ir3: make mergedregs a property of the variant
c052087038c : freedreno/ir3: re-work assembler API
ffe62e1b6c5 : freedreno/ir3: pass variant to postsched
38df3f899da : freedreno/ir3: decouple regset from gpu gen
47decc88c2b : freedreno/ir3: move mergedreg state out of reg
46cdcf590b8 : freedreno/ir3: convert regmask_t to struct
d53dc6c3768 : freedreno/fdl6: rework layout code a bit (reduce linear align to 64 bytes)
3a9ab3b6e96 : freedreno/a6xx: FETCHSIZE is PITCHALIGN
6269405a2ba : virgl: replace all dup() with os_dupfd_cloexec()
526910e8faa : svga: replace all dup() with os_dupfd_cloexec()
9ca2a4e6fc9 : freedreno: replace all dup() with os_dupfd_cloexec()
bd5cf70d3db : etnaviv: replace all dup() with os_d